Lead Full-Stack Machine Learning & DevOps Engineer, AI/ML Prototyping & Production
Location: Remote
Team: Therapeutics & Innovations
Reports To: Director of Artificial Intelligence
About Natera
Natera is a global leader in cell-free DNA testing, revolutionizing personalized healthcare through genomics. Our Therapeutics and Innovations unit is pioneering how AI intersects with clinical applications in drug discovery, clinical development, and diagnostics.
The Opportunity
We are seeking a Senior Full-Stack ML Engineer to bridge the gap between cutting-edge AI/ML research and real-world clinical impact. This role is ideal for someone with a software engineering background who thrives on transforming early-stage ML prototypes into scalable, production-ready applications.
You’ll work alongside a team of brilliant machine learning scientists who are developing compelling tools for therapeutic and diagnostic applications. Your role is to take those V1 alpha-stage prototypes—already scientifically validated—and bring them to life as polished, secure, reliable software tools ready for internal or clinical deployment.
Key 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.
Qualifications
- 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
- 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.
- Demonstrated ability to work autonomously and prioritize in a fast-paced, interdisciplinary environment.
Preferred Qualities
- 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