GenAI Engineer

GTT•San Francisco, CA

9h•Hybrid

About The Position

Our client is seeking a GenAI Engineer to build specialized production agents that support insight synthesis, evidence-grounded claims, audience personalization, and early content-quality or compliance checks. This role will work within established architecture patterns to code agent logic, integrations, tests, evaluations, and structured outputs consumed by a larger GenAI application. The team's preference is for candidates to be based on the West Coast, ideally in San Francisco. Remote candidates will also be considered, provided they can work Pacific Time hours. The team is targeting candidates at the Sr. Associate Consultant level (5–8 years of experience) through Consultant level (7–10 years of experience).

Requirements

Strong Python or TypeScript production engineering experience.
Hands-on experience coding GenAI agents with retrieval, grounding, tool calling, and structured responses.
Experience with automated evaluations, testing, citation/provenance logic, and failure handling.
Strong AWS, Amazon Bedrock, and AgentCore experience.
Ability to work independently and deliver production-ready components.

Nice To Haves

Experience with insight synthesis, evidence-grounded generation, personalization, or content-quality automation.
Experience with pharmaceutical, clinical, promotional, or regulated content workflows.
Familiarity with Veeva, Adobe platforms, or regulated content-management systems.

Responsibilities

Build production GenAI agents using tool calling, retrieval, grounding, and structured outputs.
Integrate agents with APIs, content repositories, document systems, and other agents.
Implement validation, citations, provenance, and controls to reduce unsupported outputs.
Write automated tests and evaluations for agent accuracy, behavior, and failure cases.
Deliver deployable production code within established architecture and engineering standards.