Lead GenAI Engineer Apollo Professional Solutions, Inc. - 3.8 South San Francisco, CA Job Details Full-time | Contract $90 - $93 an hour 14 hours ago Benefits Health insurance Dental insurance 401(k) Vision insurance Life insurance Qualifications AI models Performance monitoring Systems integration Software engineering Enterprise software Application Architecture Design (Architecture design skill) Software implementation Generative models Integration Architecture Design (Architecture design skills) Enterprise solutions implementation Application deployment AI platforms (beyond public GPTs) Enterprise software systems development Infrastructure architecture design Microservices AWS Model deployment Enterprise Integration Cloud Native Design Production monitoring Distributed computing AI-driven automation Model evaluation Python Design (software development lifecycle) Generative AI Providing code feedback Full Job Description Lead Generative AI Engineer (Senior Level)

Location:

Bay Area Preferred (

Hybrid:

1-2 days onsite per week)

Remote Consideration:

Candidates outside the Bay Area must maintain 4-6 hours of daily overlap with Pacific Time Shape the Future of AI-Powered Content Creation Our client is seeking a highly experienced Lead Generative AI Engineer to architect and build a next-generation agentic AI platform that empowers commercial marketing teams to create personalized, data-driven content at scale. This is a hands-on senior engineering role for a builder, architect, and technical leader who can design complex AI systems while actively developing production-grade solutions. You will lead the architecture and development of a stateful, headless GenAI application that orchestrates multiple AI agents, integrates enterprise services, and generates structured content outputs for downstream marketing platforms. If you have deep expertise in Generative AI, Large Language Models (LLMs), multi-agent systems, AWS, Amazon Bedrock, RAG architectures, and enterprise-scale software engineering , this is an opportunity to make a significant impact on a cutting-edge AI initiative. What You'll DoAI Architecture & Platform Development Design and build a production-grade, stateful Generative AI application focused on personalized content generation. Architect multi-agent workflows that coordinate AI agents, enterprise systems, and content services. Develop scalable, API-first microservices and structured data contracts. Create headless services that generate structured JSON and HTML content blueprints for downstream content assembly platforms. Establish technical standards, development patterns, and architecture best practices. Generative AI Engineering Implement multi-turn conversational experiences with context retention and memory management. Build advanced Retrieval-Augmented Generation (RAG) and grounding frameworks to produce accurate, trusted outputs. Design and manage application state, agent memory, conversation history, and clarification workflows. Develop streaming AI experiences with robust error handling and observability. Create reusable AI-generated outputs including structured content, tables, charts, citations, and other dynamic assets. Enterprise Integration & Leadership Integrate AI solutions with enterprise platforms, content repositories, and data services. Evaluate emerging AI technologies and make key architectural decisions. Review code, mentor engineers, and provide technical leadership across the development lifecycle. Drive implementation from architecture through deployment while remaining deeply involved in hands-on development. Required QualificationsTechnical Expertise Extensive experience designing and deploying production Generative AI applications. Strong software engineering background using Python and/or TypeScript . Expertise in microservices architecture and distributed systems. Proven experience building stateful, multi-turn, and multi-agent AI applications.

Deep understanding of:

Retrieval-Augmented Generation (RAG) AI grounding techniques Application state and memory management AI evaluations and performance monitoring Production observability and reliability Architecture & Development Experience designing API-first platforms and structured service contracts. Expertise developing headless applications that deliver structured outputs to downstream systems. Experience integrating AI applications with enterprise platforms, content repositories, and business systems. Ability to define architecture, establish coding standards, make technical decisions, conduct code reviews, and deliver high-quality production code. Cloud & AI Platforms Strong experience with: AWS Cloud Services Amazon Bedrock AgentCore Modern AI orchestration frameworks and enterprise AI infrastructure Preferred Qualifications Experience with content generation platforms, content-as-code frameworks, and personalization technologies. Familiarity with enterprise content management or marketing technology platforms such as: Workfront Veeva Vault PromoMats Adobe Experience Manager (AEM) Assets Comparable enterprise content ecosystems Experience working within pharmaceutical, healthcare, life sciences, or other highly regulated industries. Background supporting commercial marketing, digital content operations, or customer engagement initiatives. Why This Opportunity? This role offers the chance to lead the design and development of a sophisticated multi-agent Generative AI platform while working at the forefront of LLM applications, AI orchestration, enterprise content generation, and cloud-native architecture . You'll have significant influence over technical strategy, architecture decisions, and the future direction of a transformative AI solution. #

WCH Pay:

$90.00 - $93.00 per hour Expected hours: 40.0 per week

Benefits:

401(k) Dental insurance Health insurance Life insurance Vision insurance

Work Location:

In person