Lead GenAI Engineer

Job Overview

We are seeking a Senior/Lead GenAI Engineer to design, architect, and build a production-grade, stateful, headless GenAI application for enterprise content creation and personalization. The platform will leverage agentic AI, multi-agent orchestration, RAG, enterprise data, and content services to help commercial marketers create grounded and personalized content. This is a hands-on engineering leadership role, not a coordination-only position. The ideal candidate will define the architecture, make key technical decisions, establish development patterns, review engineering work, and personally develop critical production components.

Key Responsibilities

• Design and develop production-grade GenAI and agentic AI applications using modern LLM technologies.
• Architect stateful, multi-turn, multi-agent workflows with conversation history, memory, clarification flows, and error handling.
• Build headless GenAI services that generate structured JSON/HTML content blueprints for downstream enterprise platforms.
• Develop scalable API-first microservices and structured contracts for GenAI applications.
• Implement RAG, grounding, memory, evaluations, and enterprise data integration.
• Integrate GenAI applications with enterprise platforms, APIs, data services, and content repositories.
• Build streaming and interactive GenAI experiences supporting multi-turn conversations and real-time responses.
• Design mechanisms for rendering structured outputs including tables, charts, citations, and reusable content components.
• Leverage AWS, Amazon Bedrock, and AgentCore to build and deploy enterprise GenAI solutions.
• Establish coding standards, architectural patterns, testing strategies, and engineering best practices.
• Make key technical and architectural decisions and provide technical guidance to other engineers.
• Conduct code reviews and ensure production-quality, scalable, maintainable code.
• Implement production observability, monitoring, evaluation, logging, and error handling for GenAI applications.
• Collaborate with product, data, engineering, and business stakeholders to translate requirements into scalable technical solutions.

Required Qualifications

• Strong hands-on experience architecting and developing production GenAI/LLM applications.
• Strong Python or TypeScript development experience.
• Experience with microservices, REST APIs, API-first architecture, and structured contracts.
• Strong experience with Agentic AI and multi-agent orchestration.
• Experience developing stateful and multi-turn GenAI applications.
• Hands-on experience with RAG, grounding, memory, evaluations, and GenAI observability.
• Strong experience with AWS and Amazon Bedrock.
• Experience with Amazon Bedrock AgentCore.
• Experience integrating GenAI applications with enterprise systems, data platforms, and content repositories.
• Experience developing headless services that generate structured outputs such as JSON and HTML.
• Strong understanding of production software engineering, testing, deployment, scalability, and reliability.
• Ability to independently propose architecture, make technical decisions, and deliver production code.
• Strong communication and technical leadership skills.

Preferred Qualifications

• Experience with content generation, content-as-code, personalization, or marketing technology platforms.
• Experience with Workfront, Veeva Vault PromoMats, AEM Assets, or similar enterprise content management platforms.
• Experience working in commercial pharma or other regulated environments.
• Experience building enterprise applications involving content approval, compliance, governance, or controlled workflows.
• Experience with cloud-native deployment, CI/CD, monitoring, and production operations.