Senior Generative AI Engineer

Role Overview

The Senior Generative AI Engineer is responsible for designing, building, and deploying Natera’s Generative AI and Machine Learning solutions. The role needs excellent hands-on AI engineering excellence to build robust, accurate, and reliable AI solutions. This role requires deep expertise in Generative AI and machine learning engineering at scale, with a passion for building solutions that directly impact patient outcomes and clinical innovation.

In this role, you will develop enterprise-grade AI/ML solutions that power internal workflows (R&D, Lab Ops, Clinical Trials, Billing, Patient/Provider engagement) to automate business processes.

You will also build cutting-edge AI solutions leveraging agentic architecture, retrieval-augmented generation (RAG), vector search, feature stores, LLMOps, experimentation, observability, and compliance-first AI pipelines.

Key Responsibilities

• Design, build, and operate LLM-powered systems used in production, from initial design through deployment and iterations

• Build scalable agentic AI automation solutions, selecting appropriate patterns (reasoning, memory, agent frameworks, MCP’s, workflow orchestration, fine-tuning) based on business requirements

• Implement GenAI patterns such as RAG, tool/function calling, and multi-step workflows, selecting approaches based on accuracy, reliability and cost

• Develop and maintain data ingestion and retrieval pipelines, especially for unstructured or semi-structured documents

• Fine-tune and adapt open-source or commercial LLMs for domain-specific tasks when appropriate

• Set quality, evaluation, and reliability standards for GenAI systems, including testing, monitoring, observability, and failure handling

• Make system-level tradeoffs across model choice, latency, cost, accuracy, and operational complexity, and guide teams through those decisions

• Deploy and monitor GenAI services on AWS, optimizing for latency, cost, and system stability

• Collaborate with product managers and domain experts to translate requirements into technical solutions

• Establish golden paths (templates, examples, docs) and contribute to shared GenAI libraries, patterns, and best practices used by other engineers

• Provide technical guidance and mentorship to mid-level engineers

Qualifications

Required:

• 8+ years of experience in software engineering, ML engineering, or applied AI

• Proven experience building and operating LLM-based systems in production

• Strong Python skills and experience with PyTorch and/or Hugging Face

• Experience building agentic AI solutions using agent frameworks (LangChain, CrewAI etc.) and agent execution engines (AWS Bedrock etc.)

• Solid understanding of RAG architectures, embeddings, vector databases, and prompt orchestration

• Experience deploying AI systems on AWS (e.g., SageMaker, Bedrock, EKS/ECS, Lambda, S3)

• Strong debugging skills and comfort working across model, data, and infrastructure layers

• Ability to work independently on complex problems and communicate clearly with cross-functional partners

Preferred:

• Masters degree or PhD in Computer Science, AI/ML, engineering or related field

• Experience in healthcare, pharma, diagnostics, or other regulated industries

• Familiarity with AI governance frameworks, bias detection, explainability, and compliance (e.g., HIPAA, CLIA, FDA)