Principal AI Engineer

Natera is seeking a Principal AI Engineer to set technical direction and build the Vector Store GenAI Platform for document intelligence and retrieval across its Real-World Data organization. The role owns architecture and hands-on delivery of retrieval, document processing, and ingestion systems, while improving platform quality and supporting downstream AI workflows.

Responsibilities:

• Own platform architecture and hands-on delivery for the Vector Store GenAI Platform, including search and retrieval, document processing and chunking, ingestion pipelines, and APIs that serve downstream AI workflows
• Set technical direction for hybrid search and retrieval quality; evaluate embedding models and retrieval approaches through working implementations, POCs, and benchmarks, and drive adoption of what works in production
• Advance document parsing and chunking so clinical content is indexed in a way that supports accurate, structured, and faceted retrieval across common document types
• Define and build stable, reproducible retrieval for agent and re-extraction workloads, including durable content identifiers, flexible context assembly, versioned indices, and quality or confidence signals
• Strengthen document classification and ingestion visibility so source material is discoverable, operable, and measurable at scale across historical and ongoing data flows
• Continuously improve retrieval quality through better deduplication, clinical concept normalization, and exploration of promising retrieval methods where they add clear value
• Integrate LLM capabilities into existing production systems with attention to performance, scalability, cost, observability, and safe operation in a regulated environment
• Partner with clinical AI, engineering, product, and SME stakeholders to prioritize workstreams, define success metrics, and sequence roadmap investments without disrupting the live platform
• Provide principal-level technical leadership through architecture decisions, design reviews, clear documentation, mentoring influence, and pragmatic tradeoffs across accuracy, latency, cost, and delivery timelines

Requirements:

• Bachelor's or Master's degree in Computer Science, Engineering, or a related technical field
• 10+ years of software engineering experience, including substantial ownership of production systems at scale
• 5+ years building and shipping AI/ML-powered applications in production, with deep hands-on experience in retrieval-augmented systems, vector search, and document-centric AI pipelines—including indexing, retrieval quality, evaluation, and integration with downstream LLM or agent systems
• Demonstrated track record as a principal or equivalent IC: setting technical direction for a platform or multi-team capability, making architecture decisions that stick, and personally delivering critical path production code
• Strong hands-on expertise in Python and modern software engineering practices, including testing, code review, workflow orchestration, and agile delivery in large existing codebases
• Experience designing and operating AI systems in cloud environments
• experience with CI/CD, observability, and production support is expected
• Proven ability to work independently as an architecture-plus-build IC—influencing without direct authority, aligning stakeholders, and delivering end-to-end from strategy through integration and rollout—with strong communication across technical and non-technical audiences
• an advanced degree or background in a clinical or life sciences discipline is a plus
• AWS strongly preferred
• Experience with clinical or structured healthcare documents and document-centric search or RAG systems is strongly preferred
• Experience in healthcare, life sciences, or other regulated industries is strongly preferred
• Experience designing retrieval interfaces used by agents or multi-step LLM workflows is a plus