Principal ML Engineer

Summary

Join Natera as a Principal AI Scientist to lead the development of novel ML/AI approaches for translational research and drug development. You will bridge research innovation and production delivery, leveraging large-scale multimodal datasets and high-performance computing. Key responsibilities include model research and development, productionization and MLOps, scientific leadership and collaboration, and mentorship. This role requires a PhD in a relevant field and 8+ years of experience applying ML/AI to real-world problems in healthcare. Preferred qualifications include prior work with EHR/LIMS data and publications in biomedical AI/ML. Natera offers competitive benefits, including comprehensive medical, dental, vision, life and disability plans, free testing for employees and their families, fertility care benefits, and more.

Requirements

• PhD in Computer Science, Bioinformatics, Computational Biology, Statistics or equivalent practical experience
• 8+ years applying ML/AI to real-world problems in healthcare, life sciences, genomics or digital pathology
• Proficiency in Python and deep-learning frameworks (PyTorch, TensorFlow or Keras)
• Hands-on experience integrating LLMs and/or computer-vision models into production pipelines
• Strong communication skills with demonstrated cross-functional leadership

Responsibilities

• Lead development of novel ML/AI approaches for translational research and drug development
• Bridge research innovation and production delivery alongside AI engineers, data scientists, clinicians, and product teams
• Leverage unique, large-scale multimodal datasets and high-performance computing infrastructure
• Select, fine-tune and optimize foundation models (e.g., LLMs, U-Net, ViT, transformers, GNNs, diffusion/embedding models for multimodal data)
• Prototype and benchmark novel architectures for complex tasks across sequencing, imaging and clinical data
• Build agentic systems to automate sophisticated workflows
• Design and implement scalable, observable, and maintainable ML pipelines on AWS (SageMaker, EC2/GPU, Lambda, ECS/EKS)
• Containerize models (Docker/Kubernetes), develop APIs or batch services, and integrate into CI/CD workflows
• Contribute to reusable tooling (prompt libraries, feature extractors, evaluation harnesses) and high-performance retrieval strategies (vector DBs, RAG)
• Ensure data governance, privacy and compliance (HIPAA, GDPR) throughout model development and deployment
• Partner with domain experts to define scientific questions, shape the ML roadmap and prioritize strategic data problems
• Rapidly test hypotheses, ship prototypes/MVPs and define evaluation metrics (accuracy, latency, interpretability, robustness, fairness)
• Communicate complex technical concepts clearly to cross-functional stakeholders and drive data-driven decision making
• Provide technical leadership and mentorship to junior engineers and scientists
• Foster best practices in code quality, testing, reproducibility and documentation
• Publish high-impact research in peer-reviewed journals or conferences

Preferred Qualifications

• Prior work with EHR/LIMS data processing or bioinformatics pipelines
• Publications or open-source contributions in biomedical AI / ML
• Familiarity with agent frameworks (e.g., LangChain, MCP) and automated decision-support workflows
• Experience with vector databases and semantic search (Pinecone, Weaviate)
• Hands-on expertise with AWS ML services, container orchestration (Docker, Kubernetes) and API development

Benefits

• Comprehensive medical, dental, vision, life and disability plans for eligible employees and their dependents
• Free testing in addition to fertility care benefits
• Pregnancy and baby bonding leave
• 401k benefits
• Commuter benefits
• A generous employee referral program