AI and Agentic Engineer II

Exelixis•Alameda, CA

15h•Onsite

About The Position

The Engineer II - AI and Agentic is responsible for designing, building, and deploying production-grade agentic applications that automate multi-step IT and business workflows across Exelixis. This role delivers spec-driven, testable, and secure AI solutions, contributes to platform patterns and reusable components, while advancing the engineering standards.

Requirements

Bachelor's degree in Computer Science, Artificial Intelligence, Data Science, Software Engineering, or a related field and 5 years of related experience; or Master’s degree in Computer Science, Artificial Intelligence, Data Science, Software Engineering, or a related field and 3 year or related experience; or Equivalent combination of education and experience.
2 - 4 years of relevant experience in AI application, data science, automation, or related technical work, including hands-on experience building or contributing to LLM-enabled applications, agentic workflows, API integrations.
Intermediate to Advanced proficiency in Python and/or JavaScript/TypeScript, including modular design, testing, and packaging.
Intermediate proficiency with agent frameworks and agentic patterns: tool use, planning/execution loops, guardrails, evaluation, and prompt/version management.
Intermediate proficiency building and consuming REST APIs, and integrating enterprise systems with OAuth/JWT, secrets management, and secure data handling.
Intermediate proficiency with CI/CD, automated testing (unit/integration), linting, and observability for AI applications.
Intermediate understanding of security best practices, architecture design principles, and responsible AI/data governance.
Intermediate communication skills, written and verbal, and demonstrated ability to collaborate with cross-functional stakeholders and mentor junior engineers.
Intermediate experience with cloud AI platforms — preferably AWS Cloud, AWS Bedrock, and Databricks Mosaic AI — and vector stores or retrieval-augmented generation (RAG) patterns.
Intermediate knowledge of AI-native engineering using Claude Code, Codex, GitHub Copilot, or equivalent coding agents.

Nice To Haves

Experience delivering evaluation frameworks, red-teaming, or LLM observability tooling.

Responsibilities

Design and deliver end-to-end agentic applications and multi-agent workflows that automate IT and business processes.
Convert prototypes into hardened, production-ready services with clear specifications, modular design, robust error handling, and comprehensive test coverage.
Integrate LLMs, prompts, tools, APIs, and enterprise data sources (e.g., Bedrock, Databricks Mosaic AI, MCP servers) into reliable use cases.
Implement CI/CD pipelines, automated evaluation harnesses, observability, and artifact versioning for AI/agent workloads.
Author architecture notes, runbooks, SOPs, and technical documentation to support adoption, operability, and maintainability.
Lead prompt/spec reviews, code reviews, threat modeling exercises, and release-readiness gates.
Apply and evangelize secure-by-design and responsible AI principles, including data governance, privacy, and safe prompting aligned to organizational policy.
Contribute reusable components, patterns, and internal libraries to the platform.
Partner with product managers, security, and platform teams to translate business needs into scalable technical solutions.
Performs other duties as assigned.
Complies with all policies and standards.