Machine Learning Engineer, Model Development

This is a fully remote position, open to applicants in United States.

📋 Description

• Develop and assess AI-driven biomarkers utilizing multimodal data, such as whole-slide images, clinical variables, and molecular information, to forecast patient outcomes, treatment efficacy, and molecular characteristics.

• Play a role in the creation and evaluation of self-supervised foundational models and subsequent machine-learning frameworks, including multiple-instance learning, time-to-event/hazard models, segmentation, and classification.

• Create and assess techniques to enhance model robustness and reproducibility across various scanners, institutions, staining methods, and patient demographics.

• Investigate and implement interpretability strategies to clarify model decisions, foster clinician confidence, and promote actionable model enhancements.

• Develop and refine tools and workflows that facilitate efficient and reproducible model development, experimentation, validation, and deployment.

• Conduct thorough model evaluation and analysis, clearly communicate findings, and document experiments and technical choices.

• Collaborate with machine learning scientists and engineers as well as product teams, biostatistics, clinical development, and regulatory/quality partners throughout the model development and validation process.

• Assist with regulatory and quality documentation related to AI model development and validation.

• Contribute to peer-reviewed publications, conference presentations, and external academic or industry collaborations.

⛳️ Requirements

• Over 1 year of experience in developing machine-learning or deep-learning models using PyTorch (or TensorFlow), including relevant master's or graduate research experience.

• Knowledge of oncology and biomarker development, encompassing cancer biology and treatment pathways, clinical endpoints, risk stratification, and what constitutes a clinically actionable biomarker.

• Experience with real-world datasets and evaluating machine-learning models using suitable metrics and validation techniques.

• Proficient in Python programming with a solid understanding of modern software development practices, including version control, testing, and code reviews.

• Ability to analyze experimental outcomes, troubleshoot model behaviors, and clearly communicate findings.

• Capacity to collaborate effectively with ML engineers, scientists, and cross-functional partners.

• Experience with intricate clinical datasets, including medical imaging, multi-omics, longitudinal patient records, or data from clinical studies and multi-institutional cohorts.

• Familiarity with weakly supervised learning, multiple-instance learning, survival analysis, or similar methodologies.

• Experience with self-supervised representation learning or foundational models.

• Understanding of dataset shifts and variations across sites, devices, scanners, or acquisition protocols.

• Exposure to machine learning in regulated healthcare settings, including Software as a Medical Device (SaMD), FDA 510(k)/De Novo, design controls, or CLIA/LDT validation.

• Research experience showcased through publications, conference presentations, internships, or academic projects.

• Familiarity with cloud-based machine learning development, including distributed training, workflow orchestration, experiment tracking, or reproducible pipelines.

🏝️ Benefits

• Equity

• 401k matching

• Unlimited paid time off (PTO)