Machine Learning Engineer (Model Dev)

Role overview

This role focuses on building AI biomarkers that inform personalized cancer therapy decisions by analyzing clinical and pathology data. The engineer will work across the full model-development lifecycle, from prototyping and experimentation through validation and production deployment, contributing to challenging problems in medical AI including digital pathology modeling and pathology foundation model advancement.

Responsibilities

- Develop and evaluate AI-based biomarkers using multimodal data, including whole-slide images, clinical variables, and molecular data, to predict patient outcomes, treatment benefit, and molecular traits - Contribute to self-supervised foundation models and downstream ML methods including multiple-instance learning, time-to-event or hazard models, segmentation, and classification - Improve model robustness and reproducibility across scanners, institutions, staining protocols, and patient populations - Apply interpretability methods to explain model decisions, build clinician trust, and drive actionable improvements - Build tools and workflows that support reproducible experimentation, validation, and deployment - Collaborate with ML scientists and engineers alongside biostatistics, clinical development, product, and regulatory partners - Support regulatory and quality documentation and contribute to peer-reviewed publications and external collaborations

Requirements

- 1+ years developing machine-learning or deep-learning models using PyTorch or TensorFlow, including master's-level or graduate research experience - Familiarity with oncology and biomarker development, including cancer biology, treatment pathways, clinical endpoints, and risk stratification - Experience evaluating ML models on real-world datasets using appropriate metrics and validation approaches - Strong Python programming with modern software development practices including version control, testing, and code review - Ability to analyze experimental results, troubleshoot model behavior, and communicate findings clearly - Effective collaboration with ML engineers, scientists, and cross-functional partners

Nice to have

- Experience with complex clinical datasets such as medical imaging, multi-omics, longitudinal records, or multi-institutional cohorts - Familiarity with weakly supervised learning, multiple-instance learning, or survival analysis - Self-supervised representation learning or foundation model experience - Understanding of dataset shift across sites, devices, scanners, or acquisition protocols - Exposure to regulated healthcare ML including SaMD, FDA 510(k) or De Novo pathways, design controls, or CLIA/LDT validation - Publications, conference presentations, or academic research output - Cloud-based ML development including distributed training, workflow orchestration, experiment tracking, or reproducible pipelines

Benefits and work setup

- Base salary range of $140,000–$180,000, with equity, 401k matching, and unlimited paid time off