Lead Machine Learning & DevOps Engineer

Summary

Join Natera's Therapeutics and Innovations team as a Lead Full-Stack Machine Learning & DevOps Engineer and play a pivotal role in translating cutting-edge AI/ML research into real-world clinical applications. You will be responsible for transforming early-stage ML prototypes into scalable, production-ready applications. Collaborate with machine learning scientists, product leads, and clinical stakeholders to ensure alignment between engineering implementation and scientific and clinical goals. This role demands expertise in full-stack engineering, cloud infrastructure, AI model lifecycle management, and DevOps practices. You will work autonomously, taking ownership of projects from prototype to deployment, and continuously improve products based on feedback. The position offers the opportunity to contribute directly to the advancement of AI in healthcare and work in a dynamic, innovative environment.

Requirements

• 5+ years of experience in software engineering, ideally with a focus on ML or scientific computing
• Proven experience taking ML models or tools from prototype to production in a cloud environment
• Deep proficiency with: Python, Flask/FastAPI or Django (for APIs/services)
• JavaScript/TypeScript with React or similar (for front-end interfaces)
• Cloud platforms like AWS, GCP, or Azure (especially GPU usage)
• Production-scale, multi-GPU AI inference frameworks like vLLM and DeepSpeed
• Docker, Kubernetes, and related container/orchestration technologies
• Demonstrated ability to work autonomously and prioritize in a fast-paced, interdisciplinary environment

Responsibilities

• Productionize ML prototypes: Translate alpha-stage tools (e.g., Jupyter notebooks, python packages) into scalable, secure, and maintainable production systems
• Full-stack engineering: Build and integrate both back-end services and front-end interfaces that are performant and user-friendly
• Cloud and GPU infrastructure: Design and deploy applications using GPU-accelerated cloud infrastructure (AWS); including multi-GPU inference using frameworks such as vLLM and DeepSpeed for serving large-scale foundation models
• AI Model Lifecycle: Oversee the full model lifecycle with versioning (MLFlow), performance monitoring (W&B), and updating strategies (A/B testing)
• Autonomous development: Operate independently with minimal oversight, taking ownership from handoff to final deployment, and iteratively improving products based on internal and external feedback
• Cross-functional collaboration: Work closely with ML scientists, product leads, and clinical stakeholders to align engineering implementation with scientific and clinical goals
• DevOps & CI/CD: Set up and manage robust CI/CD pipelines, monitoring tools, and testing frameworks to ensure reliability and reproducibility
• Security & Compliance: Ensure that tools are developed with appropriate authentication, data privacy, and (where needed) HIPAA or regulatory compliance considerations

Preferred Qualifications

• Experience with experiment tracking, model registry, and observability tools (e.g., MLflow, W&B) is highly desired
• Familiarity with model-serving tools (e.g., Triton, TorchServe, TensorFlow Serving) is a plus
• Experience working in a regulated or health-tech environment is a bonus, but not required
• Product mindset with an eye for usability, performance, and security
• Comfortable reading scientific code and engaging with ML researchers
• Passion for health innovation, biotech, or clinical impact
• Experience building internal tools or developer platforms is a plus

Benefits

• Competitive Benefits - Employee benefits include comprehensive medical, dental, vision, life and disability plans for eligible employees and their dependents
• Additionally, Natera employees and their immediate families receive free testing in addition to fertility care benefits
• Other benefits include pregnancy and baby bonding leave, 401k benefits, commuter benefits and much more
• We also offer a generous employee referral program!