Pathrobotics

<h2><span>Build the Path Forward</span></h2>
<p>At Path Robotics, we’re building the future of embodied intelligence. Our AI-driven systems enable robots to adapt, learn, and perform in the real world closing the skilled labor gap and transforming industries. We go beyond traditional methods, combining perception, reasoning, and control to deliver field-ready AI that is risk-aware, reliable, and continuously improving through real-world use.</p>
<p>Big, hard problems are our everyday work, and our team of intelligent, humble, and driven people make the impossible possible together.</p>
<p><span>We are seeking a skilled and motivated Machine Learning Engineer with expertise in modern robotics and manipulation to join our Robot Learning team to build agentic AI systems for industrial applications. The ideal candidate will have experience in robotics, with a focus on developing and implementing advanced manipulation techniques, motion control systems, and planning algorithms for autonomous robots. This role involves working closely with cross-functional teams to design, test, and deploy innovative solutions that improve the performance and capabilities of our robotic systems. </span></p>
<h2><span>What You’ll Do</span></h2>
<ul>
<li><span>Work on the development and deployment of behavioral cloning (BC), reinforcement learning (RL), and diffusion models to solve complex robotic tasks.</span></li>
<li><span>Leverage multi-modal data, including image-based data, force, and torque to enhance robotic manipulation and control.</span></li>
<li><span>Design and implement vision-language-action (VLA) models for more intelligent and responsive robotic systems.</span></li>
<li><span>Craft strategies for the entire solution's lifecycle, including data collection, fleet learning, and continuous learning.</span></li>
<li><span>Develop, optimize, and deploy learning-based methods for robot control and object manipulation algorithms on a fleet of industrial robotic cells.</span></li>
<li><span>Collaborate with hardware and software teams to integrate manipulation, control, and planning algorithms into robotic platforms.</span></li>
<li><span>Stay updated with the latest advancements in robotics, control theory, and planning algorithms.</span></li>
</ul>
<h2><span>Who You Are</span></h2>
<ul>
<li><span>Ph.D. or Master’s degree in Robotics, Mechanical Engineering, Electrical Engineering, Computer Science, or a related field.</span></li>
<li><span>Proven track record in publishing at top conferences (e.g., NeurIPS, ICLR, ICML, CoRL, RLC).</span></li>
<li><span>Experience with robotic simulation tools (e.g., Isaac Sim, MuJoCo).</span></li>
<li><span>Experience with machine learning techniques applied to robot manipulation.</span></li>
<li><span>Experience building models from scratch and deploying them in real-world applications.</span></li>
<li><span>Experience with pose estimation, segmentation, active perception, and affordance-based bin picking.</span></li>
<li><span>Strong programming skills in languages such as C++ or Python.</span></li>
<li><span>Experience with robotic simulation tools (e.g., Isaac Sim, MuJoCo).</span></li>
<li><span>Proven track record of deploying scalable solutions for autonomous robotic systems.</span></li>
<li><span>Strong communication skills, with the ability to convey complex technical concepts to a diverse audience.</span></li>
</ul>
<h2><span>Why You'll Love It Here</span></h2>
<ul>
<li>Daily free lunch to keep you fueled and connected with the team</li>
<li>Flexible PTO so you can take the time you need, when you need it</li>
<li>Comprehensive medical, dental, and vision coverage</li>
<li>6 weeks fully paid parental leave, plus an additional 6–8 weeks for birthing parents (12–14 weeks total)</li>
<li>401(k) retirement plan through Empower</li>
<li>Generous employee referral bonuses—help us grow our team!</li>
</ul>
<h2><span>Who We Are</span></h2>
<p>At Path Robotics we love coming to work to solve interesting and tough challenges but also because our ideas are welcomed and valued. We encourage unique thinking and are dedicated to creating a diverse and inclusive environment. All qualified applicants will receive consideration for employment without regard to race, color, religion, gender, gender identity or expression, sexual orientation, national origin, genetics, disability, age, or veteran status.</p>
<p>If you require a reasonable accommodation to participate in the application process or any part of the hiring process, please contact HR@path-robotics.com. We are committed to providing equal access and will work with qualified individuals to ensure a fair and accessible hiring experience. We will respond to your request within 48 hours.</p>
<p> </p>
<p> </p>

Machine Learning Engineer, Robot Learning

<p><span><strong>Build the Path Forward</strong></span></p>
<p>At Path Robotics, we’re building the future of embodied intelligence. Our AI-driven systems enable robots to adapt, learn, and perform in the real world closing the skilled labor gap and transforming industries. We go beyond traditional methods, combining perception, reasoning, and control to deliver field-ready AI that is risk-aware, reliable, and continuously improving through real-world use.</p>
<p>Big, hard problems are our everyday work, and our team of intelligent, humble, and driven people make the impossible possible together.</p>
<p>You will play a mission-critical role in architecting our data platform, enabling our machine learning and robotics teams to move faster, experiment more effectively, and deploy AI solutions into production.</p>
<p>This is an opportunity to push our data infrastructure forward and drive value across the business. Reporting to the Data Engineering Manager, you will collaborate with a talented team of data engineers, machine learning engineers and software engineers to deliver clean, reliable, and scalable data products that fuel experimentation, production models, and cutting-edge AI development.</p>
<h2>What You’ll Do</h2>
<ul>
<li>Partner with software, ML, robotics, and analytics teams to understand their data needs and turn them into well-modeled tables and data products.</li>
<li>Develop and extend data models and pipelines assets that support experimentation, model training and validation, reporting, and business decisions.</li>
<li>Model large-scale, multi-modal data such as sensor streams, application telemetry, system logs, and unstructured blob data. Identify opportunities for this data to support our mission. </li>
<li>Monitor pipeline health and data quality, troubleshoot failures, and improve tests and alerting in order to build trust in our data assets.</li>
<li>Apply and strengthen the team's standards for governance, lineage, documentation, and data contracts.</li>
<li>Write clean, tested, well-documented Python and SQL, and take part in team code reviews.</li>
<li>Improve the data platform's usability, performance, and tooling, and evangelize enhancements among our user base.</li>
</ul>
<h2>Who You Are</h2>
<ul>
<li>2+ years of experience in data engineering or a closely related role, building and supporting production data pipelines.</li>
<li>Strong proficiency in SQL and Python.</li>
<li>Hands-on experience with tools like AWS, Snowflake, Dagster, dbt, or an equivalent modern data stack.</li>
<li>Solid grasp of data modeling, warehousing concepts, and pipeline orchestration.</li>
<li>Solid grasp of data modeling, warehousing concepts, and pipeline orchestration.</li>
<li>Curious about the problems your data solves. You enjoy working directly with stakeholders to deliver data that drives real decisions.</li>
<li>You take ownership of your work, communicate clearly, and want to learn from and contribute to an experienced team.</li>
<li><strong>Bonus:</strong> experience working with sensor data, robotics logs, manipulation data, or other high-volume, real-world datasets.</li>
</ul>
<p><span><strong>Why You’ll Love Working Here</strong></span></p>
<ul>
<li>Daily free lunch to keep you fueled and connected with the team</li>
<li>Flexible PTO so you can take the time you need, when you need it</li>
<li>Comprehensive medical, dental, and vision coverage</li>
<li>6 weeks fully paid parental leave, plus an additional 6–8 weeks for birthing parents (12–14 weeks total)</li>
<li>401(k) retirement plan through Empower</li>
<li>Generous employee referral bonuses—help us grow our team!</li>
</ul>
<p><strong>Who We Are</strong></p>
<div>At Path Robotics we love coming to work to solve interesting and tough challenges but also because our ideas are welcomed and valued. We encourage unique thinking and are dedicated to creating a diverse and inclusive environment. All qualified applicants will receive consideration for employment without regard to race, color, religion, gender, gender identity or expression, sexual orientation, national origin, genetics, disability, age, or veteran status.</div>
<div> </div>
<div>If you require a reasonable accommodation to participate in the application process or any part of the hiring process, please contact <a href="mailto:HR@path-robotics.co" target="_blank">HR@path-robotics.co</a>m. We are committed to providing equal access and will work with qualified individuals to ensure a fair and accessible hiring experience. We will respond to your request within 48 hours.</div>
<p><strong><em>Regulatory and Compliance Requirements</em></strong><br /><em>This position may support work performed under U.S. Government contracts and requires compliance with applicable federal regulations, including FAR and DFARS where applicable. </em><em>The role may involve access to export-controlled information subject to ITAR and/or EAR. Candidates must be able to comply with U.S. export control regulations, which may include meeting the definition of a “U.S. Person” where required. </em><em>This position may also involve handling Controlled Unclassified Information (CUI) and requires adherence to company and federal data protection and confidentiality standards. Employment may be contingent upon successful completion of a background check consistent with applicable requirements.</em></p>
<p> </p>

Data Engineer

<h2><strong>Build the Path Forward</strong></h2>
<p>At Path Robotics, we’re attacking a trillion dollar opportunity - doing things that have never been done before to support an industry hurting from a lack of skilled labor. Big, hard problems are what Path tackles every day, and our people are our greatest asset to get that job done. Our intelligent, hardworking team of people do the impossible every single day, yet remain incredibly kind, humble, and always ready to support one another.</p>
<p>We are building an elite robotics and perception team, and we are looking for an exceptional hands-on <strong>Perception Engineer</strong> to own <strong>the vision a real-time control loop closes on</strong>.</p>
<h2><strong>What you'll do</strong></h2>
<ul>
<li><strong>The real-time perception pipeline, end to end</strong> — sensing through extraction and geometry to the output another engineer's control loop acts on, at rate, on embedded hardware, inside a budget you set and measure.</li>
<li><strong>Robustness where the signal is being actively degraded.</strong> Getting a reliable measurement out of imagery that something is deliberately ruining is the hardest part of the job and the part that decides whether the whole system works.</li>
<li><strong>Making the estimate honest about its own failure.</strong> A confident wrong answer is the most dangerous thing this role can produce, because the loop will act on it. We want estimates that know when they are wrong and say so early enough to matter.</li>
<li><strong>Geometric estimation against a known model</strong> — recovering where things are, well enough to work against, from partial and imperfect data, and knowing when the geometry does not actually support the answer you just produced.</li>
<li><strong>Choosing and proving the instruments.</strong> You will evaluate sensing options, run the experiments that settle them, and defend the choice with numbers. This is a real part of the role, not an occasional errand.</li>
<li><strong>Setting the technical direction</strong> as the perception work grows toward learned methods.</li>
</ul>
<p><strong>Who You Are</strong></p>
<ul>
<li>You have closed a real-time loop on what a camera saw, on real hardware, and something physical moved in response. You can state its rate, its measured end-to-end latency, and how you measured it — not the model's inference time, the whole chain.</li>
<li>First-principles depth in classical vision and 3-D geometry — camera geometry, triangulation, registration and where it fails, calibration, and propagating error properly rather than quoting a single number.</li>
<li>Real-time segmentation or feature extraction on degraded imagery, deployed rather than benchmarked, and an understanding of why thin and low-contrast structures break the standard metrics and losses.</li>
<li>Strong, modern, production C++, and ROS 2.</li>
<li>GPU-accelerated inference on embedded hardware under a hard per-frame budget — and the habit of measuring the tail rather than the mean.</li>
<li>A physical accuracy claim you can defend — measured against something independent of the system that produced it, with bias reported separately from repeatability.</li>
</ul>
<h2><strong>Why You'll Love It Here</strong></h2>
<ul>
<li>Daily free lunch to keep you fueled and connected with the team</li>
<li>Flexible PTO so you can take the time you need, when you need it</li>
<li>Comprehensive medical, dental, and vision coverage</li>
<li>6 weeks fully paid parental leave, plus an additional 6–8 weeks for birthing parents (12–14 weeks total)</li>
<li>401(k) retirement plan through Empower</li>
<li>Generous employee referral bonuses—help us grow our team!</li>
</ul>
<h2><strong>Who We Are</strong></h2>
<p>At Path Robotics we love coming to work to solve interesting and tough challenges but also because our ideas are welcomed and valued. We encourage unique thinking and are dedicated to creating a diverse and inclusive environment. All qualified applicants will receive consideration for employment without regard to race, color, religion, gender, gender identity or expression, sexual orientation, national origin, genetics, disability, age, or veteran status.</p>
<p>If you require a reasonable accommodation to participate in the application process or any part of the hiring process, please contact HR@path-robotics.com. We are committed to providing equal access and will work with qualified individuals to ensure a fair and accessible hiring experience. We will respond to your request within 48 hours.</p>

Real-Time Robotics Perception Engineer

<p><span><strong>Build the Path Forward</strong></span></p>
<p>At Path Robotics, we’re building the future of embodied intelligence. Our AI-driven systems enable robots to adapt, learn, and perform in the real world closing the skilled labor gap and transforming industries. We go beyond traditional methods, combining perception, reasoning, and control to deliver field-ready AI that is risk-aware, reliable, and continuously improving through real-world use.</p>
<p>Big, hard problems are our everyday work, and our team of intelligent, humble, and driven people make the impossible possible together.</p>
<p>Manufacturing demands exceptionally high performance, reliability, and adaptability. Processes like welding involve fast, complex, and poorly modeled physics that traditional simulators struggle to capture - especially in the long tail of real-world conditions.</p>
<p>We are building intelligent robotic systems that learn directly from data by combining neural world models with reinforcement learning. Our goal is to give robots the ability to <strong>learn, predict, and plan</strong> in complex manufacturing environments by replacing or augmenting classical physics simulators with fast, high-fidelity learned ones.</p>
<p>We are seeking a Senior Machine Learning Engineer to lead the development of a neural welding simulator - a learned world model that captures the visual and physical dynamics of welding and enables large-scale RL training. This role sits at the intersection of generative modeling, robotics, and applied physics. It is research-heavy by design, while still grounded in production reality.</p>
<p>We are hiring two Senior Machine Learning Engineers with complementary specializations:</p>
<ul>
<li><strong>Senior Machine Learning Engineer, World Models</strong></li>
<li><strong>Senior Machine Learning Engineer, Reinforcement Learning</strong></li>
</ul>
<h2><span><strong>Senior ML Engineer, World Models</strong></span></h2>
<h3><strong>What You’ll Do</strong></h3>
<ul>
<li>Build action-conditioned world models that predict how the welding process evolves under changes to robot motion and process parameters.</li>
<li>Model relationships among inputs, system state, physical dynamics, and resulting weld quality.</li>
<li>Develop multimodal models using data such as video, 3D scans, thermal measurements, electrical signals, robot state, and process parameters.</li>
<li>Explore latent dynamics, video prediction, generative modeling, and spatiotemporal representations.</li>
<li>Improve long-horizon rollout accuracy, physical plausibility, temporal consistency, and computational efficiency.</li>
<li>Quantify model uncertainty and identify conditions under which predictions are unreliable.</li>
<li>Validate learned predictions against real-world welding data.</li>
<li>Integrate the model into RL, planning, process-optimization, evaluation, and synthetic-data workflows.</li>
<li>Prevent downstream optimization systems from exploiting inaccuracies in the learned model.</li>
<li>Translate promising research into scalable training and inference systems.</li>
</ul>
<h2><span><strong>Senior ML Engineer, Reinforcement Learning</strong></span></h2>
<h3><strong>What You’ll Do</strong></h3>
<ul>
<li>Develop reinforcement learning approaches for optimizing welding decisions and process outcomes.</li>
<li>Define state, observation, action, and reward representations based on measurable manufacturing objectives.</li>
<li>Train and evaluate policies using learned world models, traditional simulation, offline datasets, and controlled real-world experiments.</li>
<li>Develop offline, model-based, or constrained RL methods suitable for limited and expensive physical interaction.</li>
<li>Optimize across competing objectives such as weld quality, cycle time, reliability, energy use, and equipment constraints.</li>
<li>Design methods that account for uncertainty, distribution shift, delayed outcomes, and sparse or imperfect reward signals.</li>
<li>Diagnose reward exploitation, unsafe behavior, policy instability, and model exploitation.</li>
<li>Establish reliable offline and real-world policy evaluation methods.</li>
<li>Partner with controls, welding, robotics, world-model, data, and ML infrastructure engineers.</li>
<li>Translate research prototypes into dependable training, evaluation, and deployment systems.</li>
</ul>
<h2><strong>Who You Are</strong></h2>
<ul>
<li>Master’s or PhD in Computer Science, Robotics, Machine Learning, or related field, or equivalent practical experience.</li>
<li>Experience developing and deploying reinforcement learning algorithms on real-world systems.</li>
<li>Proficiency in Python and deep learning frameworks such as PyTorch or TensorFlow.</li>
<li>Experience with simulation environments (e.g., MuJoCo, Isaac Gym).</li>
<li>Solid understanding of probability, statistics, and optimization.</li>
<li>Experience with training and deploying ML models in production systems.</li>
</ul>
<h2><strong>Why You'll Love It Here</strong></h2>
<ul>
<li>Daily free lunch to keep you fueled and connected with the team</li>
<li>Flexible PTO so you can take the time you need, when you need it</li>
<li>Comprehensive medical, dental, and vision coverage</li>
<li>6 weeks fully paid parental leave, plus an additional 6–8 weeks for birthing parents (12–14 weeks total)</li>
<li>401(k) retirement plan through Empower</li>
<li>Generous employee referral bonuses—help us grow our team!</li>
</ul>
<h2><strong>Who We Are</strong></h2>
<p>At Path Robotics we love coming to work to solve interesting and tough challenges but also because our ideas are welcomed and valued. We encourage unique thinking and are dedicated to creating a diverse and inclusive environment. All qualified applicants will receive consideration for employment without regard to race, color, religion, gender, gender identity or expression, sexual orientation, national origin, genetics, disability, age, or veteran status.</p>
<p>If you require a reasonable accommodation to participate in the application process or any part of the hiring process, please contact HR@path-robotics.com. We are committed to providing equal access and will work with qualified individuals to ensure a fair and accessible hiring experience. We will respond to your request within 48 hours.</p>

Senior Machine Learning Engineer (Reinforcement Learning/World Model)

<h2><span>Build the Path Forward</span></h2>
<p>At Path Robotics, we’re building the future of embodied intelligence. Our AI-driven systems enable robots to adapt, learn, and perform in the real world closing the skilled labor gap and transforming industries. We go beyond traditional methods, combining perception, reasoning, and control to deliver field-ready AI that is risk-aware, reliable, and continuously improving through real-world use.</p>
<p>Big, hard problems are our everyday work, and our team of intelligent, humble, and driven people make the impossible possible together.</p>
<p>We are standing up a new Robot Learning team focused on whole-body loco-manipulation for precision tasks in heavy manufacturing. </p>
<p>We are seeking a Senior Machine Learning Engineer (Tech Lead) for this new team. You write code, set the technical direction, make the architectural decisions the team builds on, mentor junior and intermediate engineers, and help shape how the team works.</p>
<h2>What You’ll Do</h2>
<ul>
<li>Set the ML technical direction for the team, architectural choices on perception, reasoning, and action generation; training methodology; data strategy; the path from research bet to deployed capability. As one of the first senior hires, you are designing the approach, not extending it.</li>
<li>Own the architectural workstreams that define the team's research and engineering bets — multiple core build streams across action-policy learning, world-model-based supervision, and policy-orchestration interfaces.</li>
<li>Design hybrid physics-ML architectures for the integrated loco-manipulation stack. Manipulation, locomotion, and the whole-body control coupling between them are not separable on legged platforms; sub-millimetre continuous-trajectory precision at the tool requires the whole-body controller to compensate for base motion in real time. Today on fixed bases; tomorrow on mobile platforms. The integration is the hard problem; you own its design.</li>
<li>Own the cross-functional partnerships with hardware teams, domain experts, customer-facing assurance standards, and upstream / downstream teams. Drive a phased deployment strategy that builds production trust over time.</li>
<li>Mentor and shape the team, guide junior and intermediate ICs across software, ML, robotics, and perception backgrounds; establish code-quality standards, review practices, and engineering norms; help identify and attract next hires. You write code throughout — this is a tech-lead role, not a step away from the work.</li>
</ul>
<p><span><strong>Who You Are</strong></span></p>
<ul>
<li>Ph.D. or Master's degree in Robotics, Mechanical Engineering, Electrical Engineering, Computer Science, or a related field or equivalent experience.</li>
<li>5+ years of hands-on robot learning experience. You have shipped sim-to-real policies on real robots, across different tasks or platforms.</li>
<li>Demonstrated technical leadership and mentorship. You have made architectural decisions on robot learning systems that others built on, and you have meaningfully shaped the development of more-junior engineers as a tech lead. This can be in academia (leading a lab subgroup, advising students) or industry.</li>
<li>Deep sim-to-real expertise — domain randomisation, system identification, teacher-student distillation, sim-to-online fine-tuning. You can design a transfer strategy for a novel problem.</li>
<li>Full-stack robot learning — fluent across simulation construction, policy training, data collection, real-world deployment, and failure diagnosis.</li>
<li>Physics-informed ML or hybrid control experience — PINNs, neural ODEs, MPC with learned dynamics, process-model-conditioned generation, or similar.</li>
<li>A defensible view on visual-reasoning-centric substrates for grounded spatial / physical reasoning.</li>
<li>Push-back willingness — you can defend a non-obvious architectural commitment under pressure, and change your mind on evidence.</li>
<li>Strong programming skills in Python and C++; production-quality code with reproducibility, testing, and maintainability discipline.</li>
<li>Strong communication skills, able to convey complex technical concepts to a diverse audience.</li>
<li>Demonstrated independent technical authority — you have set technical direction in a tech-lead capacity, leading a research subgroup, owning an architecture across multiple ICs' work, or making the architectural call on a high-profile project.</li>
</ul>
<p><strong>Strongly Preferred:</strong></p>
<ul>
<li>Edge inference depth (TensorRT, ONNX, edge-class deployment).</li>
<li>Loco-manipulation experience — locomotion, whole-body control, and manipulation on legged platforms (quadrupeds, humanoids). The coupling between the three is the hard problem; direct hands-on experience or a defensible architectural view both count.</li>
<li>Precision manipulation or surgical robotics — sub-mm accuracy tasks.</li>
<li>Flow-matching action-head design at depth — direct experience with the architectural pattern.</li>
<li>Visual self-supervised representation learning experience on robot or 3D-vision tasks.</li>
<li>Multi-skill workflow or hierarchical policy design — skill sequencing, failure detection, control mode transitions.</li>
<li>Experience building ML capability from early stage — first or second ML engineer on a team, or built a research group's infrastructure from scratch.</li>
</ul>
<p><span><strong>Why You’ll Love Working Here</strong></span></p>
<ul>
<li>Daily free lunch to keep you fueled and connected with the team</li>
<li>Flexible PTO so you can take the time you need, when you need it</li>
<li>Comprehensive medical, dental, and vision coverage</li>
<li>6 weeks fully paid parental leave, plus an additional 6–8 weeks for birthing parents (12–14 weeks total)</li>
<li>401(k) retirement plan through Empower</li>
<li>Generous employee referral bonuses—help us grow our team!</li>
</ul>
<p><span><strong>Who We Are</strong></span></p>
<p>At Path Robotics we love coming to work to solve interesting and tough challenges but also because our ideas are welcomed and valued. We encourage unique thinking and are dedicated to creating a diverse and inclusive environment. All qualified applicants will receive consideration for employment without regard to race, color, religion, gender, gender identity or expression, sexual orientation, national origin, genetics, disability, age, or veteran status.</p>
<p>If you require a reasonable accommodation to participate in the application process or any part of the hiring process, please contact HR@path-robotics.com. We are committed to providing equal access and will work with qualified individuals to ensure a fair and accessible hiring experience. We will respond to your request within 48 hours.</p>
<p> </p>

Pathrobotics

Open jobs at Pathrobotics

Machine Learning Engineer, Robot Learning

Data Engineer

Real-Time Robotics Perception Engineer

Senior Machine Learning Engineer (Reinforcement Learning/World Model)

Senior Machine Learning Engineer (Tech Lead), Robot Learning, Loco- Manipulation

Working for Pathrobotics?

Featured companies