{"active":true,"apply_url":"https://jobs.ashbyhq.com/midjourney/9beaa654-e136-4e6d-b51b-4c5b3ccb7e2b/application","company":{"claimed":false,"name":"Midjourney","slug":"midjourney","website":"https://www.midjourney.com"},"countries":["US"],"employment_type":"full-time","first_seen_at":"2026-10-31T09:30:09Z","getwork_url":"https://getwork.dev/jobs/ab-midjourney-9beaa654-e136-4e6d-b51b-4c5b3ccb7e2b/","id":"ab-midjourney-9beaa654-e136-4e6d-b51b-4c5b3ccb7e2b","injection_flag":false,"last_seen_at":"2026-11-03T10:30:09Z","location":"San Francisco Bay Area Hybrid; United States","published_at":"2026-09-18T00:17:33Z","regions":["north_america"],"remote":"hybrid","role_family":"ml","salary":{"currency":"USD","max":250000,"min":237000,"period":"year","source":"structured"},"seniority":"senior","stack":[],"stack_mentioned":["pytorch"],"title":"Senior Machine Learning Engineer (Clinical Team)","untrusted_description":"WHAT YOU’LL DO\n\n1. Own the tissue-class segmentation and labeling models for the ultrasound CT clinical analysis layer, and the pipelines that make them trainable and verifiable.\n\n2. Retune across 2D per-slice, 3D volumetric, and 2D×3D fusion as reconstructed image inputs are continuously updated, and clinical indications for use expand.\n\n3. Define training/evaluation pipelines, datasets, and metrics from the ground up or from open source; map model behavior to user needs and design requirements.\n\n4. Work with data labeling contractors, expert clinicians, and our internal cloud/data teams on labeling specs, QC, and dataset versioning.\n\n5. Help productionize models into a versioned, HIPAA-bound analysis service: reproducible/low-latency inference, per-prediction confidence, drift monitoring, and safe fallbacks.\n\nWHAT WE’RE LOOKING FOR\n\n- 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.\n\n- 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.\n\n- Comfortable moving fluidly between open-ended research iteration and producing quantifiable, testable models.\n\n- Fluent in modern deep-learning tooling (e.g., PyTorch) and current development practices.\n\n- Comfortable working under design controls, where model changes carry documentation and verification weight.\n\nUSEFUL EXPERIENCE\n\n- 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.\n\n- 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.\n\n- 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).\n\n- Experience with segmentation models for ultrasound imaging, whether on synthetic or real images\n\n- ML for imaging or inverse problems in physics-based domains (CT, MRI, ultrasound, or adjacent), and comfort working alongside reconstruction/signal-processing teams.\n\n- Deploying models in versioned, auditable, high-stakes settings.\n\n- A background in anatomy, medical imaging, or body composition and prior work with existing segmentation models is a plus.","url":"https://jobs.ashbyhq.com/midjourney/9beaa654-e136-4e6d-b51b-4c5b3ccb7e2b"}