Machine Learning Engineer (Model Dev)

<h3>Accountabilities</h3><li>Develop and evaluate AI-based biomarkers using multimodal datasets, including whole-slide images, clinical variables, and molecular data, to predict patient outcomes, treatment benefit, and molecular characteristics.</li><li>Contribute to self-supervised foundation models and downstream machine-learning systems, including multiple-instance learning, survival and hazard models, segmentation, and classification.</li><li>Design and evaluate approaches that improve model robustness and reproducibility across scanners, institutions, staining protocols, and patient populations.</li><li>Investigate model interpretability techniques to explain predictions, strengthen clinician trust, and identify opportunities for model improvement.</li><li>Build and enhance tools, workflows, and pipelines that enable efficient, reproducible experimentation, validation, and deployment of machine-learning models.</li><li>Conduct rigorous model evaluation, analyze experimental results, troubleshoot model behavior, and communicate technical findings clearly.</li><li>Collaborate with ML scientists and engineers alongside product, biostatistics, clinical development, regulatory, and quality teams throughout model development and validation.</li><li>Support regulatory and quality documentation associated with AI model development, evaluation, and validation.</li><li>Contribute to peer-reviewed research, conference presentations, and collaborations with academic and industry partners.</li><h2>Requirements</h2><li>At least 1 year of experience developing machine-learning or deep-learning models using PyTorch, TensorFlow, or comparable frameworks, including relevant master's-level or graduate research experience.</li><li>Familiarity with oncology and biomarker development, including cancer biology, treatment pathways, clinical endpoints, risk stratification, and the characteristics of clinically actionable biomarkers.</li><li>Experience working with real-world datasets and applying appropriate metrics and validation methodologies to evaluate machine-learning models.</li><li>Strong Python programming skills and familiarity with modern software-engineering practices, including version control, testing, code review, and maintainable development workflows.</li><li>Ability to analyze experimental results, investigate model behavior, troubleshoot technical issues, and communicate conclusions effectively.</li><li>Strong collaboration skills and the ability to work effectively with machine-learning engineers, scientists, clinicians, and other cross-functional stakeholders.</li><li>Experience with complex clinical datasets such as medical imaging, multi-omics, longitudinal patient records, clinical studies, or multi-institutional cohorts is highly valuable.</li><li>Familiarity with weakly supervised learning, multiple-instance learning, survival analysis, or related machine-learning techniques is preferred.</li><li>Experience with self-supervised representation learning, foundation models, or large-scale model development is advantageous.</li><li>Understanding of dataset shift and variability across sites, devices, scanners, staining methods, or acquisition protocols is a plus.</li><li>Exposure to machine learning in regulated healthcare environments, including SaMD, FDA 510(k) or De Novo pathways, design controls, or CLIA/LDT validation, is desirable.</li><li>Research experience demonstrated through publications, conference presentations, internships, or academic projects is valued.</li><li>Familiarity with cloud-based ML development, distributed training, workflow orchestration, experiment tracking, or reproducible ML pipelines is a plus.</li><h2>Benefits</h2><li>Base salary of<strong>$140,000–$180,000 per year</strong>, depending on experience, qualifications, and other relevant factors.</li><li>Equity as a core component of the overall compensation package.</li><li>401(k) plan with employer matching.</li><li>Unlimited paid time off (PTO).</li><li>Remote work environment.</li><li>Opportunity to work on challenging medical-AI problems with potential to improve cancer diagnosis, treatment decisions, and patient outcomes.</li><li>Collaboration with experienced ML scientists and engineers as well as clinical, biostatistics, product, and regulatory professionals.</li><li>Opportunities to contribute to publications, conference presentations, and external academic or industry collaborations.</li><li>Inclusive and equal-opportunity workplace committed to bringing together diverse perspectives and backgrounds.</li>