Spaitial

SpAItial is pioneering the next generation of World Models, pushing the boundaries of generative AI, computer vision, and the simulation of reality. We are moving beyond 2D pixels to build models that natively understand the physics and geometry of our world. Our mission is to redefine how industries, from robotics and AR/VR to gaming and cinema, generate and interact with physically-grounded 3D environments.<div> </div>We're looking for bold, innovative individuals driven by a passion for pushing the boundaries of generative 3D AI. You should thrive in an environment where creativity meets technical challenge and be fearless in tackling the hardest problems in 3D world modeling. Our team is built on a foundation of dedication and a shared commitment to excellence, so we value people who take immense pride in their work and place the collective goals of the team above personal ambition. As a part of SpAItial, you'll be at the forefront of building World Models that bridge generative AI and the physical world. If you're ready to make an impact, embrace the unknown, and collaborate with a talented group of visionaries, we want to hear from you.<div> </div>We're seeking PhD Research Interns to work with our research team on open problems in 3D generation and reconstruction. You should have strong knowledge of at least one of our core areas, such as generative video and diffusion models, scene representations like Gaussian splats and radiance fields, or 3D reconstruction from per-scene optimization to feed-forward models. Over a 5-7 month internship, you will own a well-defined research question with the goal of publishing a paper. <div> </div>Responsibilities<ul><li>You will explore novel research directions in 3D generation, reconstruction, and world models. </li><li>You will design, implement, and evaluate state-of-the-art methods, turning innovative research ideas into working systems and prototypes. </li><li>You will be working closely with our research team.</li><li> You will also present your findings and contribute to scientific publications targeting leading conferences in computer vision, computer graphics, and machine learning, such as CVPR, ICCV, ECCV, SIGGRAPH, NeurIPS, and ICLR.</li></ul>Key Qualifications<ul><li>Currently enrolled in the third year or beyond of a PhD in computer science, computer vision, computer graphics, machine learning, or a related field.</li><li>2-3 first-author papers at top-tier conferences such as CVPR, ICCV, ECCV, SIGGRAPH, NeurIPS, or ICLR.</li><li>Knowledge of at least one of: generative models (diffusion or video models), neural scene representations, or 3D reconstruction.</li></ul><div> </div>At SpAItial, we are committed to creating a diverse and inclusive workplace. We welcome applications from people of all backgrounds, experiences, and perspectives. We are an equal opportunity employer and ensure all candidates are treated fairly throughout the recruitment process.

PhD Research Intern, 3D World Models

SpAItial is pioneering the next generation of World Models, pushing the boundaries of generative AI, computer vision, and the simulation of reality. We are moving beyond 2D pixels to build models that natively understand the physics and geometry of our world. Our mission is to redefine how industries, from robotics and AR/VR to gaming and cinema, generate and interact with physically-grounded 3D environments.We’re seeking a Research Engineer to own the backend that serves our world models. You will build and run the inference systems behind our product and API, turning frontier research models into fast, reliable, and scalable services. This is a hands-on role for someone who has already owned production APIs in an AI system and can work closely with researchers to bring new models to users.Responsibilities<ul><li>Own the inference services and APIs that power our product, from request to generated output.</li><li>Optimize serving performance, reliability, and cost at scale. Maximize GPU utilization and minimize device memory footprint.</li><li>Apply latest techniques for improving inference performance.</li><li>Deploy research models as production services, including customer-specific configurations.</li><li>Work with research and product colleagues to bring new models to users.</li></ul>Key qualifications<ul><li>3+ years of software engineering in an AI, machine learning, or computer vision product environment.</li><li>Experience designing and owning production APIs.</li><li>Strong Python, and experience shipping containerized services on GPU inference platforms.</li><li>Hands-on GPU inference performance work: profiling, memory, batching, and cold start.</li><li>Familiarity with 3D or computer vision data is a strong plus.</li></ul>At SpAItial, we are committed to creating a diverse and inclusive workplace. We welcome applications from people of all backgrounds, experiences, and perspectives. We are an equal opportunity employer and ensure all candidates are treated fairly throughout the recruitment process.

ML Inference Engineer

SpAItial is pioneering the next generation of World Models, pushing the boundaries of generative AI, computer vision, and the simulation of reality. We are moving beyond 2D pixels to build models that natively understand the physics and geometry of our world. Our mission is to redefine how industries, from robotics and AR/VR to gaming and cinema, generate and interact with physically-grounded 3D environments.We’re seeking a Research Engineer to push the quality of our 3D reconstruction. You should have command of the latest scene representations, such as Gaussian splats and radiance fields, and of reconstruction methods across the full range, from per-scene optimization to feed-forward models. We are looking for someone who knows the field well enough to choose the right representation and method for a problem, build it, and then make it better. This is a hands-on role for an engineer with deep reconstruction knowledge and strong coding skills.Responsibilities<ul><li>Advance the quality of 3D reconstruction, from research ideas to working methods.</li><li>Work across the full range of reconstruction problems, including geometry, appearance, materials and lighting, sparse or incomplete observations, dynamic scenes, and large-scale environments.</li><li>Build and improve reconstruction methods across the full spectrum, from per-scene optimization to feed-forward models.</li><li>Stay at the frontier of scene representations, implement new ones as they appear, and adopt or extend them where they win.</li><li>Tune losses, priors, and optimization strategies to improve fidelity, robustness, and efficiency.</li><li>Build rigorous evaluations on public and internal benchmarks, and use them to drive decisions.</li><li>Collaborate with research and engineering colleagues to bring successful methods into production systems.</li></ul>Key qualifications<ul><li>Bachelor’s or Master’s degree, or equivalent experience, in computer science, computer vision, graphics, or a related field.</li><li>Deep, hands-on knowledge of modern scene representations, for example Gaussian splats and radiance fields, and the ability to weigh their trade-offs.</li><li>Hands-on experience across the reconstruction spectrum, from per-scene optimization to feed-forward models.</li><li>Solid understanding of multi-view geometry, camera models, and rendering.</li><li>Strong experience with deep learning frameworks, including large experiments and comparisons you can defend.</li><li>Strong coding skills, and the ability to take a method from a paper to a working implementation.</li><li>A PhD or publications in reconstruction are a plus, not a requirement.</li></ul>At SpAItial, we are committed to creating a diverse and inclusive workplace. We welcome applications from people of all backgrounds, experiences, and perspectives. We are an equal opportunity employer and ensure all candidates are treated fairly throughout the recruitment process.

Research Engineer - 3D Reconstruction

SpAItial is pioneering the next generation of World Models, pushing the boundaries of generative AI, computer vision, and the simulation of reality. We are moving beyond 2D pixels to build models that natively understand the physics and geometry of our world. Our mission is to redefine how industries, from robotics and AR/VR to gaming and cinema, generate and interact with physically-grounded 3D environments.We’re seeking a Research Scientist to push the state of the art in 3D reconstruction. You should have command of the latest scene representations, such as Gaussian splats and radiance fields, and of reconstruction methods across the full range, from per-scene optimization to feed-forward models. We are looking for someone who knows the field well enough to choose the right representation and method for a problem, and then improve on it. This is a senior, hands-on research role for someone who has already done reconstruction research across more than one representation.Responsibilities<ul><li>Advance the state of the art in 3D reconstruction, from research ideas to working methods.</li><li>Work across the full range of reconstruction problems (geometry, appearance, materials, lighting and dynamics, from sparse or incomplete observations), and novel view synthesis, including neural rendering and feed-forward view generators.</li><li>Design losses, priors, and optimization strategies that improve fidelity, robustness, and efficiency.</li><li>Build rigorous evaluations on public and internal benchmarks, and use them to drive decisions.</li><li>Collaborate with research and engineering colleagues to bring successful methods into production systems.</li></ul>Key qualifications<ul><li>PhD in computer vision, graphics, or a related field; publications at top venues (CVPR, ICCV, ECCV, SIGGRAPH, NeurIPS).</li><li>Deep, hands-on knowledge of modern scene representations, for example Gaussian splats and radiance fields, and the ability to weigh their trade-offs.</li><li>Research experience across the reconstruction spectrum, from per-scene optimization to feed-forward models.</li><li>Deep understanding of multi-view geometry, camera models, and rendering.</li><li>Strong experience with deep learning frameworks.</li></ul>At SpAItial, we are committed to creating a diverse and inclusive workplace. We welcome applications from people of all backgrounds, experiences, and perspectives. We are an equal opportunity employer and ensure all candidates are treated fairly throughout the recruitment process.

Research Scientist - 3D Reconstruction & Novel View Synthesis

SpAItial is pioneering the next generation of World Models, pushing the boundaries of generative AI, computer vision, and the simulation of reality. We are moving beyond 2D pixels to build models that natively understand the physics and geometry of our world. Our mission is to redefine how industries, from robotics and AR/VR to gaming and cinema, generate and interact with physically-grounded 3D environments.We're seeking a Research Scientist to train the policies that turn a world model into a robot that acts. You will own vision-language-action (VLA) and world-action models (WAM) end to end, starting, including data, backbone, action representation, training runs, and the evaluation that tells us whether a policy is genuinely competent or merely lucky. A world model that understands geometry and physics still doesn't act on its own; the policy is what closes that gap. This is a senior, hands-on research role for someone who has already trained manipulation policies that worked, and who can say precisely why the ones that didn't failed.Responsibilities<ul><li>Own the training pipeline for vision-language-action (VLA) and world-action models (WAM) end to end, from data to a policy running on a robot.</li><li>Contribute to setting the technical direction for embodied research at SpAItial.</li><li>Close the sim-to-real gap through domain randomization, system identification, and calibration, and build evaluation that predicts real-world transfer.</li><li>Adapt VLM backbones for control: encoder choice and adapter strategies, co-training.</li><li>Curate and weight the training mix across heterogeneous robot datasets, spanning differing embodiments, action spaces, and sensor setups.</li><li>Design action representation and decoding, including tokenization, chunking, diffusion, and flow-matching action experts.</li><li>Build the world-model components that predict future observations conditioned on action.</li><li>Run post-training: supervised fine-tuning onto target embodiments, and RL for robustness beyond demonstrations.</li></ul>Key Qualifications<ul><li>A PhD in robotics, machine learning, or computer vision with a robot learning focus, from the PhD alone or followed by industry experience.</li><li>Publications at top venues such as (CoRL, RSS, ICRA, IROS or CVPR, ICCV, ECCV, NeurIPS), open-source work, and/or deployed systems.</li><li>Deep experience with modern robot policy designs (VLA, WAM, diffusion), trained end to end rather than fine-tuned from a released checkpoint.</li><li>Strong imitation learning fundamentals, and familiarity with RL fine-tuning of pretrained policies.</li><li>Fluency with VLM backbones and how to adapt them for control.</li><li>Expert Python and PyTorch, with multi-node distributed training experience (FSDP or equivalent).</li></ul>At SpAItial, we are committed to creating a diverse and inclusive workplace. We welcome applications from people of all backgrounds, experiences, and perspectives. We are an equal opportunity employer and ensure all candidates are treated fairly throughout the recruitment process.

Spaitial

Open jobs at Spaitial

PhD Research Intern, 3D World Models

ML Inference Engineer

Research Engineer - 3D Reconstruction

Research Scientist - 3D Reconstruction & Novel View Synthesis

Research Scientist - Robot Learning (VLA / WAM)

Working for Spaitial?

Featured companies