Lead Generative AI Engineer

Pharmaceutical Company; South San Francisco (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

Pharmaceutical Company seeks a senior Lead GenAI Engineer to design and implement a production-grade, stateful GenAI application for grounded marketing content. You will architect multi-agent workflows, manage persistence, and deliver API-first contracts for downstream systems in a production environment.

The role requires strong Python/TypeScript coding, experience with microservices and AWS Bedrock, and hands-on leadership in architecture and code delivery.

Qualifications

• Production-grade GenAI applications experience.
• Strong hands-on programming in Python or TypeScript.
• Experience building microservices and API-driven applications.
• Proven experience with stateful, multi-turn conversational apps and multi-agent orchestration.
• Experience designing API-first architectures and machine-consumable responses.
• Familiarity with RAG, grounding, context management and evaluation frameworks.
• Experience building streaming interfaces and interactive workflows.
• Experience integrating AI apps with enterprise services and downstream systems.
• Strong knowledge of observability, error handling and production quality controls for GenAI systems.
• Hands-on AWS Bedrock and AgentCore experience with production code delivery.

Responsibilities

• Design and build a stateful, headless GenAI application that supports grounded, personalized content generation for commercial marketing use cases.
• Develop and manage agentic workflows that coordinate multiple AI agents, tools, and enterprise services.
• Implement multi-turn conversational workflows with persistent project context, memory, conversation history, and state management.
• Define API-first contracts and generate structured JSON or HTML content blueprints for downstream systems.
• Build integrations with enterprise platforms and services using APIs, microservices, and data contracts.
• Implement retrieval-augmented generation (RAG) and grounding to improve output accuracy.
• Support streaming responses, clarification flows, and interactive conversation history.
• Enable structured presentation with tables, charts, citations, and reusable results.
• Ensure observability, error handling, and quality controls for production readiness.
• Lead architecture decisions, review code, and contribute production-ready software.

Skills

GenAI architecture

Python

TypeScript

Microservices

API-driven applications

Stateful multi-turn apps

Agent orchestration

RAG / grounding

Streaming interfaces

Production code delivery

AWS Bedrock

AgentCore

Tools

Amazon Bedrock

Job description

Lead GenAI Engineer (Senior Role)

Focus: Agentic Content-Application Architecture and Orchestration

Role Overview

We are seeking a senior, hands-on Lead GenAI Engineer to architect and build a stateful, headless Generative AI application that enables commercial marketers to create grounded, personalized content. The application will orchestrate multiple AI agents and enterprise services, maintain conversational and project context, and produce structured outputs such as JSON or HTML blueprints for downstream content assembly.

This role requires a strong combination of GenAI architecture, agent orchestration, backend engineering, and production implementation. The ideal candidate will lead technical decisions while actively developing and delivering production-ready code.

Key Responsibilities

• GenAI Application Architecture: Design and build a stateful, headless GenAI application that supports grounded, personalized content generation for commercial marketing use cases.
• Multi-Agent Orchestration: Develop and manage agentic workflows that coordinate multiple AI agents, tools, and enterprise services.
• State and Context Management: Implement multi-turn conversational workflows with persistent project context, memory, conversation history, and state management.
• Structured Content Generation: Design API-first contracts and generate structured JSON or HTML content blueprints that downstream systems can consume reliably.
• Enterprise Integrations: Build integrations with enterprise platforms and services using APIs, microservices, and well-defined data contracts.
• Retrieval and Grounding: Implement retrieval-augmented generation (RAG), context grounding, evaluation frameworks, and mechanisms to improve output accuracy and reliability.
• Streaming and User Interaction: Support streaming responses, clarification flows, conversation history, error handling, and other interactive application capabilities.
• Structured Response Presentation: Enable the generation and presentation of structured responses, including tables, charts, citations, and reusable results.
• Production Readiness: Implement observability, evaluation, error handling, and quality controls for reliable production operation.
• Technical Leadership: Establish architecture patterns and coding standards, make technical decisions, conduct code reviews, and contribute directly to production code.

Required Qualifications

• Demonstrated experience architecting and building production-grade Generative AI applications.
• Strong hands-on programming skills in Python or TypeScript.
• Experience developing microservices and API-driven applications.
• Proven experience with stateful, multi-turn conversational applications and multi-agent orchestration.
• Experience designing API-first architectures, structured output contracts, and machine-consumable responses.
• Strong understanding of RAG, grounding, context management, memory, and GenAI evaluation.
• Experience building streaming interfaces and interactive workflows, including clarification handling and conversation history.
• Experience integrating AI applications with enterprise services and downstream systems.
• Familiarity with observability, error handling, testing, and production quality controls for GenAI systems.
• Strong hands-on experience with AWS and Amazon Bedrock , including AgentCore.
• Ability to lead architecture and engineering decisions while remaining actively involved in implementation and code delivery.

Preferred Qualifications

• Experience with content generation, content-as-code, personalization, or marketing technology platforms.
• Experience with enterprise content management and marketing workflow platforms such as:
• Adobe Workfront
• Veeva Vault PromoMats
• Adobe Experience Manager (AEM) Assets
• Comparable enterprise content or digital asset management platforms
• Experience supporting commercial marketing or content workflows in the pharmaceutical or life sciences industry.
• Familiarity with structured content assembly and integrating generated content into downstream enterprise publishing workflows.

Location and Work Arrangement

• Preferred location: San Francisco Bay Area.
• On-site expectations: Candidates in the Bay Area should be able to work from the office 1-2 days per week.
• Remote consideration: Candidates outside the Bay Area should be able to maintain 4-6 hours of daily working-time overlap with Pacific Time.

Ideal Candidate Profile

The ideal candidate is a senior engineer who can take ownership of the architecture and implementation of a production GenAI application. They should be comfortable designing multi-agent workflows, managing conversational and project state, integrating enterprise services, and delivering structured, grounded content outputs.

This is a hands-on engineering role, not a coordination-only or purely strategic architecture position. Strong AWS, Amazon Bedrock, and AgentCore experience is important, along with the ability to translate architectural decisions into production-ready software.