Lead GenAI Engineer

Apollo Professional Solutions, Inc.; South San Francisco (CA); On-site; USD 165,000 - 248,000; Full time

Job summary

Agentic AI Architecture in the San Francisco Bay Area is seeking a Lead GenAI Engineer to architect and build a next-generation, stateful GenAI platform for personalized content at scale.

You will lead design of multi-agent orchestration, RAG, and API-first services, while mentoring developers and delivering production-grade code.

Qualifications

• Significant hands-on experience architecting and building production GenAI applications.

Responsibilities

• Design and build a stateful, headless GenAI app for personalized content workflows.
• Architect systems coordinating multiple AI agents, services, and data sources.
• Implement multi-turn conversations maintaining context and state.
• Develop services that output structured JSON and HTML blueprints for content assets.
• Lead scalable API-first architecture and reusable service patterns.
• Build agent orchestration with routing, memory, and workflow coordination.
• Integrate AI services with enterprise platforms and data systems.
• Deliver outputs including narratives, tables, visualizations, citations.
• Implement observability, evaluation, monitoring, grounding, and reliability.

Skills

Python

TypeScript

Microservices

Multi-agent systems

API design

State management

RAG

Observability

Tools

AWS Bedrock

AgentCore

Job description

Lead GenAI Engineer (Contract)

Agentic AI Architecture, Multi-Agent Orchestration & Content Intelligence

Are you a senior-level AI engineer who enjoys designing systems from the ground up while staying hands-on with development? We are seeking a Lead GenAI Engineer to architect and build a next-generation, stateful Generative AI platform that helps commercial teams create personalized, evidence-based content at scale.

What You'll Do

• Design and build a stateful, headless GenAI application that supports personalized content creation workflows.
• Architect systems that coordinate multiple AI agents, enterprise services, and data sources.
• Implement multi-turn conversational experiences that maintain project context, application state, and user interactions over time.
• Develop services that generate structured JSON and HTML content blueprints for downstream platforms to assemble into final content assets.
• Lead the design of scalable API-first architectures, reusable service patterns, and structured data contracts.
• Build and optimize agent orchestration frameworks, including routing, state management, memory, and workflow coordination.
• Integrate AI services with enterprise platforms, content repositories, and data systems.
• Deliver AI-generated outputs including: Structured content blueprints Narrative responses Tables and data visualizations Citations and evidence references Reusable content components.
• Implement observability, evaluation, monitoring, grounding, and reliability controls for production AI systems.
• Review code, establish engineering best practices, and mentor other developers while remaining actively involved in coding and technical delivery.

Required Qualifications

• Significant hands-on experience architecting and building production Generative AI applications.
• Strong software engineering expertise with Python and/or TypeScript.
• Proven experience designing and deploying microservices-based architectures.
• Deep knowledge of: Multi-agent systems Agent orchestration Stateful AI applications Multi-turn conversational experiences Strong API design and structured contract development experience.
• Experience building headless platforms and services that generate structured outputs for downstream applications.
• Expertise integrating AI applications with enterprise platforms, content repositories, and data services.
• Hands-on experience with: Retrieval-Augmented Generation (RAG) Grounding techniques Application state and memory management AI evaluations and testing Production observability and monitoring Experience developing streaming AI experiences with: Clarification workflows Conversation history Error handling Real-time responses.
• Experience rendering structured outputs including tables, charts, citations, and reusable results.
• Demonstrated ability to define architecture, make technical decisions, establish coding standards, review engineering work, and deliver production-quality code.
• Strong experience with: AWS Amazon Bedrock AgentCore

Preferred Qualifications

• Experience building AI-driven content generation and content-as-code solutions.
• Background in personalization engines, marketing technology platforms, or AI-powered content workflows.
• Familiarity with enterprise content ecosystems such as: Workfront Veeva Vault PromoMats Adobe Experience Manager (AEM) Assets Comparable content management platforms.
• Experience working in regulated industries with structured content review and approval processes.
• Knowledge of commercial life sciences, healthcare, financial services, or other highly regulated environments.

Location & Work Arrangement

San Francisco Bay Area candidates preferred, with the ability to work onsite 1-2 days per week. Candidates outside the Bay Area must provide 4-6 hours of daily overlap with Pacific Time business hours.

Why This Opportunity?

This role offers the chance to architect and build a sophisticated enterprise GenAI platform that combines agentic AI, multi-agent orchestration, RAG, content generation, personalization, and cloud-native services. You'll have direct influence over technical strategy while remaining deeply involved in designing and delivering innovative AI solutions that drive real business impact.

Keywords:

Lead GenAI Engineer, Senior AI Engineer, Generative AI Architect, Agentic AI, Multi-Agent Systems, AI Platform Engineer, Python Engineer, TypeScript Engineer, AWS Bedrock, AgentCore, RAG Engineer, AI Orchestration, Enterprise AI, Headless Architecture, Microservices, Content Generation, AI Applications, Contract Engineering Opportunity.