Senior Data Scientist, Gen AI Application

The Opportunity

As a Sr. Data Scientist - Generative AI Applications within Genentech's Data, Digital, and Analytics (DDA) organization, you will bridge the gap between core AI infrastructure and high-impact business applications across Commercial, Medical, and Government Affairs (CMG). In this high-visibility role, you will design, build, and optimize intelligent agents and agentic workflows that reason, utilize complex tools, and automate intricate multi-step business processes. You will collaborate closely with platform engineers and business product owners to deliver seamless, reliable, and user-centric GenAI solutions that drive measurable business impact.

• Architect, build, and deploy intelligent AI agents, orchestration workflows, decision logic, and collaboration patterns for complex enterprise applications.
• Define and implement robust tool schemas, APIs, permissions, error-handling mechanisms, and human-in-the-loop escalation paths for agentic systems.
• Optimize agent behavior across key metrics including accuracy, task completion reliability, latency, cost efficiency, and end-user experience.
• Design effective memory, context retention, retrieval-augmented generation (RAG), and summarization strategies to enhance agent capabilities.
• Establish comprehensive evaluation frameworks, observability metrics, synthetic test scenarios, and trace analyses to diagnose failure modes and prevent hallucinations.
• Partner with application engineers, platform teams, and business product managers to integrate agentic systems into secure, production-grade enterprise environments.
• Standardize agent development patterns, guardrails, and best practices across the DDA organization.

Who you are

• 5+ years of professional experience in software engineering, machine learning, or GenAI application development.
• Hands-on experience designing, building, and deploying LLM-powered agents or agentic workflows in production environments.
• Strong working knowledge of prompting techniques, tool calling, structured outputs, planning mechanisms, RAG, and context management.
• Proficiency in Python, TypeScript, or a comparable production language, alongside experience with agent orchestration frameworks (e.g., LangGraph, LangChain, or custom frameworks).
• Demonstrated expertise designing APIs, tool contracts, asynchronous workflows, and integration patterns for scalable systems.

Preferred

• Experience with multi-agent architecture systems and inter-agent communication protocols (e.g., A2A, MCP).
• Experience building and deploying agentic workflows within enterprise platforms or regulated industries (biotech, pharma, finance, or healthcare).
• Familiarity with model routing, prompt versioning, fine-tuning, guardrails, and human-in-the-loop workflows.
• Strong understanding of cloud environments (AWS, AWS AgentCore), identity, access management, data privacy, and secure tool execution.
• Proven track record translating ambiguous business objectives into reliable technical agent workflows and quantifiable outcomes.

Location

This role is based in South San Francisco and offers a hybrid schedule working 3 days per week on campus. No relocation benefits are available for this posting.