Lead GenAI Engineer (Strong AWS, Amazon Bedrock, and AgentCore experience)

Position: Lead GenAI Engineer (Strong AWS, Amazon Bedrock, and AgentCore experience) Type: Contract (W2 Only) Location: South San Fransico, CA (Bay Area) - Hybrid Prefer but open to remote candidates that can do 4–6 hours of daily working overlap with Pacific Time Consultant's Title: Lead GenAI Engineer Work Location: San Fransico, CA (Bay Area preferred), with the ability to work from the office 1–2 days per week. Candidates outside the Bay Area must be able to provide 4–6 hours of daily working overlap with Pacific Time. Is Telecommuting Possible? Yes. Hybrid work is preferred for Bay Area candidates, with 1–2 days per week in the office. Remote candidates may be considered if they can maintain the required daily overlap with Pacific Time. Who Does This Position Report To? To be confirmed. Why Is There a Need for a Consultant/Contractor? To provide senior-level GenAI architecture and hands-on engineering expertise to design and build a production-ready, stateful, headless generative AI application for commercial content creation and personalization. What Is the Start Date of the Contract? ASAP What Is the Anticipated Length/Scope of the Contract? Contract duration to be confirmed. The scope includes proposing the application architecture, making key technical decisions, implementing critical components, establishing coding patterns, and delivering production-ready GenAI capabilities. What Is the Size of the Department? To be confirmed. What Projects Will the Consultant Be Involved With? The consultant will lead the technical design and implementation of an agentic content-application platform that enables commercial marketers to create grounded, personalized content. The application will coordinate multiple AI agents and enterprise services, maintain conversational and project state, and generate structured JSON or HTML content blueprints that downstream platforms can use to assemble finished content assets. The project will involve agent orchestration, enterprise integrations, retrieval-augmented generation (RAG), application memory, structured output generation, evaluation frameworks, streaming interactions, and production observability. Responsibilities: Architect and build a stateful, headless GenAI application for enterprise content creation and personalization. Design and implement multi-agent orchestration across AI agents, enterprise APIs, data services, and content repositories. Establish application architecture, technical standards, coding patterns, and API-first design principles. Develop robust services that generate structured JSON and HTML content blueprints for downstream applications. Implement conversational and project state management, multi-turn interactions, memory, and context retention. Build RAG and grounding capabilities to ensure generated content is supported by relevant enterprise information and source material. Develop streaming GenAI interfaces with clarification flows, conversation history, error handling, and resilient response management. Implement structured response rendering, including tables, charts, citations, and reusable results. Establish evaluation strategies and production observability to monitor quality, reliability, and application performance. Integrate GenAI capabilities with enterprise platforms, business systems, data services, and content repositories. Make key technical decisions, review other engineers' work, and establish scalable engineering practices. Write and deliver production-quality code while remaining actively involved in architecture and implementation. Role with the Group (manager, programmer, etc.): Senior hands-on technical lead responsible for GenAI application architecture, agentic orchestration, and implementation. This is an engineering role requiring direct coding and technical ownership, not a coordination-only or project-management position. Required Skills: Significant hands-on experience architecting and building production-grade generative AI applications. Strong software engineering experience in Python or TypeScript. Experience designing and developing microservices and API-first architectures. Demonstrated experience with stateful, multi-turn GenAI applications and multi-agent orchestration. Strong understanding of structured contracts, API schemas, and machine-readable output formats. Experience building headless services that produce structured outputs for downstream applications. Experience integrating GenAI applications with enterprise platforms, data services, and content repositories. Practical experience with retrieval-augmented generation (RAG), grounding, application state, memory, and context management. Experience developing GenAI evaluation frameworks and production observability. Experience building streaming, multi-turn GenAI interfaces with clarification flows, conversation history, and error handling. Experience rendering structured responses, including tables, charts, citations, and reusable results. Ability to propose architecture, make technical decisions, establish coding patterns, review engineering work, and deliver production code. Strong AWS, Amazon Bedrock, and AgentCore experience. Desired Skills: Experience with content generation, content-as-code, personalization, or marketing technology platforms. Experience with Workfront, Veeva Vault PromoMats, Adobe Experience Manager (AEM) Assets, or comparable enterprise content management systems. Experience working in commercial pharmaceutical or other regulated content environments. Experience designing systems that support enterprise content governance, source traceability, and reusable content components. Selling Point of the Job (Why Would Someone Want This Contract?): Opportunity to take technical ownership of a sophisticated, production-focused GenAI application that combines agentic AI, enterprise integration, and personalized content generation. The consultant will have a direct impact on architecture and implementation, making key engineering decisions and building critical components using AWS, Amazon Bedrock, and AgentCore. This is an ideal opportunity for a senior engineer who wants to build and deliver a real-world GenAI solution rather than simply oversee a team. Work Hours and Schedule (flex time? required overtime?): To be confirmed. Candidates must be able to provide 4–6 hours of daily working overlap with Pacific Time.