Senior AI/ML Engineer

Natera is a global leader in cell-free DNA testing, dedicated to oncology, women’s health, and organ health. The Senior AI/ML Engineer will design, build, and deploy Natera’s Generative AI and Machine Learning platforms, focusing on developing production-ready AI solutions that directly impact patient outcomes.

Responsibilities:

• Design and implement foundational GenAI services: vector search, prompt tuning, agent orchestration, document extraction, context/memory services, model/endpoint registry, feature/embedding stores, guardrails, and evaluation pipelines
• Build the underlying infrastructure for autonomous and semi-autonomous AI agents including support for agent collaboration, reasoning, and memory persistence, enabling continuous context-aware execution
• Build standardized APIs/SDKs that make it easy for product teams to compose, deploy, and monitor Generative AI workloads
• Ensure platform components meet enterprise-grade requirements for scalability, latency, multi-region resilience, and cost efficiency
• Stand up LLM runtimes with token/rate governance, caching, and safe tool-use
• Implement RAG at scale: ingestion pipelines, chunking/embedding policies, hybrid search, relevance/risk scoring, and feedback loops
• Build agent orchestration (single & multi-agent) with planning, tool routing, shared/persistent memory, and inter-agent communication
• Integrate tooling and APIs that allow agents to interact with internal systems, retrieve data securely, and take action under strict controls
• Collaborate with research teams to prototype and productionize multi-agent architectures for workflow automation, report generation, and data synthesis
• Implement cloud-native infrastructure for large-scale model training and serving using Kubernetes, MLflow, Terraform, and AWS-native services
• Automate data and model pipelines for RAG, LLM fine-tuning, and agent orchestration
• Integrate observability tools (Datadog or equivalent) for real-time performance, drift detection and safety monitoring of AI outputs
• Optimize compute and storage architecture to ensure cost-effective scaling of large models and multi-agent workloads
• Partner with security, data governance, SRE, and application teams to productize platform capabilities
• Embed compliance-by-design (HIPAA/CLIA/CAP/FDA/GDPR): PHI/PII handling, encryption, access controls, audit trails
• Implement guardrails: input/output filters, prompt hardening, allow/deny policies for tool execution, policy-as-code in CI/CD
• Bias/explainability hooks and automated evaluations for RAG/LLM/agents; drift and regression detection
• Establish golden paths (templates, examples, docs) and lead platform architecture reviews, code reviews, and design discussions
• Partner with data scientists, AI researchers, and product engineers to deliver reliable and maintainable AI services
• Mentor junior engineers in platform development, distributed systems, and agentic AI infrastructure concepts
• Influence cross-functional roadmaps by partnering with Product and Engineering leadership to align delivery with business needs