Midjourney

<h3>What you’ll do</h3><ol><li>Own the tissue-class segmentation and labeling models for the ultrasound CT clinical analysis layer, and the pipelines that make them trainable and verifiable.</li><li>Retune across 2D per-slice, 3D volumetric, and 2D×3D fusion as reconstructed image inputs are continuously updated, and clinical indications for use expand.</li><li>Define training/evaluation pipelines, datasets, and metrics from the ground up or from open source; map model behavior to user needs and design requirements.</li><li>Work with data labeling contractors, expert clinicians, and our internal cloud/data teams on labeling specs, QC, and dataset versioning.</li><li>Help productionize models into a versioned, HIPAA-bound analysis service: reproducible/low-latency inference, per-prediction confidence, drift monitoring, and safe fallbacks.</li></ol><h3>What we’re looking for</h3><ul><li>Strong applied ML experience with a track record of developing new models — architecting, training, and evaluating from scratch as well as benchmarking against existing models.</li><li>Experience with image segmentation (semantic/instance, 2D and ideally 3D/volumetric) and the modeling and training-data choices that make it robust across diverse patient anatomy.</li><li>Comfortable moving fluidly between open-ended research iteration and producing quantifiable, testable models.</li><li>Fluent in modern deep-learning tooling (e.g., PyTorch) and current development practices.</li><li>Comfortable working under design controls, where model changes carry documentation and verification weight.</li></ul><h3>Useful experience</h3><ul><li>Image segmentation and label generation with modern architectures (U-Net / nnU-Net, 3D U-Net, transformer-based and promptable segmentation like SAM), including the geometry that ties voxel- and mesh-level predictions back to a coordinate frame.</li><li>Learning under limited or noisy supervision: self-supervised / semi-supervised methods (masked autoencoders, contrastive pretraining like DINO/SimCLR), active learning, weak labels, and simulation-driven pretraining.</li><li>Hands-on experience with data curation for ML: building datasets from messy, real-world sources, helping to define ground truth, and managing labeling or simulation pipelines (MONAI, ITK / SimpleITK, 3D Slicer).</li><li>Experience with segmentation models for ultrasound imaging, whether on synthetic or real images</li><li>ML for imaging or inverse problems in physics-based domains (CT, MRI, ultrasound, or adjacent), and comfort working alongside reconstruction/signal-processing teams.</li><li>Deploying models in versioned, auditable, high-stakes settings.</li><li>A background in anatomy, medical imaging, or body composition and prior work with existing segmentation models is a plus.</li></ul>

Senior Machine Learning Engineer (Clinical Team)

<h3>What you’ll do</h3><ol><li>Partner with medical image reconstruction scientists / engineers to build ML components that improve reconstruction quality, speed, robustness, or quantitative accuracy.</li><li>Define training/evaluation pipelines, datasets, and metrics that map to user needs and design requirements.</li><li>Productionize models: inference performance, reproducibility, monitoring for drift/regressions, and safe fallbacks.</li><li>Collaborate on hybrid algorithms, incorporating physics and learned priors, denoisers, learned regularizers, and quality estimation.</li><li>Help build tooling for rapid experimentation as well as rigorous verification of algorithm changes.</li></ol><h3>What we’re looking for</h3><ul><li>Strong applied ML experience plus comfort with signal processing / imaging or adjacent domains.</li><li>Ability to move fluidly between research prototypes and production-quality systems.</li><li>Strong evaluation discipline: metrics, ablations, data leakage avoidance, and reproducibility.</li><li>A demonstrated track record of applying ML to physics-based or inverse problems (i.e., shipped projects, a portfolio, or publications.)</li></ul><h3>Useful experience</h3><ul><li>ML for imaging/inverse problems (or adjacent) with strong evaluation discipline and comfort with GPU performance constraints.</li><li>Pragmatic production mindset: reproducible training/inference, regression testing, and safe deployment in high-stakes contexts.</li><li>A background in computational physics or scientific computing.</li><li>Leverage ML-based methods such as PiNNs and Neural Operators to solve partial differential equations arising in ultrasound simulation and imaging.</li><li>Experience in Agentic-SciML is a plus.</li><li>Hands-on experience with data curation for ML: building datasets from messy, real-world sources, defining ground truth, and managing labeling or simulation pipelines.</li><li>Background in data assimilation: combining observations with physics-based models (Kalman filtering, variational methods, ensemble approaches, or learned variants).</li></ul>

Principal Machine Learning Engineer (Reconstruction / Quantitative Imaging)

<h3>What you’ll do</h3><ol><li>Design and implement secure cloud pipelines that ingest very large scan datasets (multi-terabyte), reliably and resumably.</li><li>Build orchestration for GPU-accelerated reconstruction and analysis with strong retry semantics, idempotency, and cost controls.</li><li>Define end-to-end data lifecycle for medical imaging: raw vs intermediate vs derived artifacts, retention policies, and reproducibility.</li><li>Implement security + compliance primitives appropriate for HIPAA/PHI: encryption in transit/at rest, key management, least privilege, audit logs, and access reviews.</li><li>Build operational tooling: monitoring, alerting, runbooks, and incident-driven improvements for a growing device fleet.</li></ol><h3>What we’re looking for</h3><ul><li>Strong experience with cloud batch/queueing/orchestration, storage systems, and data pipeline reliability.</li><li>Experience shipping production systems that handle large data volumes and failure-prone networks.</li><li>Practical security mindset (least privilege, secrets, audit logging) and comfort operating in compliance-constrained environments.</li></ul><h3>Useful experience</h3><ul><li>Building reliable data pipelines at scale (queues/orchestration, resumable uploads, GPU batch execution) with strong observability.</li><li>Security + privacy by default: encryption, least-privilege access, auditing, and practical HIPAA/PHI guardrails.</li><li>Owning the “boring” backend details that keep a lean team moving: schemas/migrations, cost controls, retries, and runbooks.</li><li>Understanding compute tradeoffs across hardware options, and specifying appropriate cloud resources.</li></ul>

Midjourney

Open jobs at Midjourney

Senior Machine Learning Engineer (Clinical Team)

Principal Machine Learning Engineer (Reconstruction / Quantitative Imaging)

Senior Cloud / Data Engineer (Data / Reconstruction / HIPAA)

Working for Midjourney?

Featured companies