Lead GenAI Engineer

Our client, a leading pharmaceutical and life sciences company, is looking to hire a Lead GenAI Engineer in the Bay Area, CA (hybrid).

Lead GenAI Engineer - Agentic Content Application Architecture

Location: Bay Area, CA preferred (hybrid, 1-2 days onsite per week)

Work Arrangement: Remote candidates considered with 4-6 hours of daily working overlap with Pacific Time

Pay Range: $50/hr - $90/hr on W2 (DOE)

Role Type: Senior-Level Contract

Job Overview

This role will focus on agentic application architecture and orchestration, coordinating multiple AI agents, enterprise services, data sources, and content repositories while maintaining conversational and project-level state. The application will generate structured JSON or HTML content blueprints that downstream platforms can use to assemble finished marketing assets.

The ideal candidate brings significant experience building production-grade GenAI applications, strong software engineering and microservices expertise, and deep hands-on experience with AWS, Amazon Bedrock, and AgentCore.

This is a senior individual-contributor and technical leadership role requiring direct involvement in architecture design, technical decision-making, implementation, and code reviews. The successful candidate will establish engineering patterns, develop critical production components, and guide other engineers in delivering a scalable and reliable GenAI solution.

Key Responsibilities

• Design and implement the architecture for a production-ready, stateful GenAI application supporting multi-turn conversations and multi-agent orchestration.
• Build and orchestrate AI agents that interact with enterprise APIs, data services, content repositories, and other business systems.
• Develop robust backend services and microservices using Python or TypeScript, following API-first design principles and well-defined service contracts.
• Implement headless GenAI services that generate structured JSON or HTML content blueprints for consumption by downstream applications and publishing platforms.
• Design application-state management, conversational memory, context retention, and clarification workflows to support complex, multi-step content-generation tasks.
• Implement retrieval-augmented generation (RAG), grounding strategies, and enterprise data integration to improve content accuracy, relevance, and consistency.
• Build streaming, multi-turn GenAI interaction patterns that support conversation history, clarification requests, error handling, and reusable results.
• Enable structured response rendering, including tables, charts, citations, and other content components required by downstream user interfaces.
• Establish evaluation frameworks, production observability, monitoring, and error-handling practices to assess output quality, reliability, and system performance.
• Make key architectural and technical decisions, establish coding standards, review other engineers' work, and contribute directly to production code.
• Integrate the application with AWS services, Amazon Bedrock, AgentCore, and relevant enterprise content and marketing technology platforms.
• Partner with product, marketing, data, and engineering stakeholders to translate business requirements into scalable technical solutions.

Required Qualifications

• Significant hands-on experience architecting, building, and deploying production GenAI applications.
• Strong software engineering skills in Python or TypeScript, with experience developing microservices and production backend systems.
• Demonstrated experience designing and implementing stateful, multi-turn, multi-agent orchestration for GenAI applications.
• Strong understanding of API-first architecture, service integration, structured data models, and contract-driven development.
• Experience building headless services that produce structured outputs, such as JSON or HTML, for downstream applications.
• Proven experience integrating GenAI solutions with enterprise platforms, APIs, data services, and content repositories.
• Hands-on experience with RAG, grounding techniques, application state, conversational memory, evaluations, and production observability.
• Experience developing streaming GenAI experiences with multi-turn conversations, clarification flows, conversation history, and robust error handling.
• Experience designing or supporting structured content rendering, including tables, charts, citations, and reusable response components.
• Strong hands-on experience with AWS, Amazon Bedrock, and AgentCore.
• Ability to own architecture decisions, establish engineering patterns, write production-quality code, and provide technical direction through code reviews.
• Strong problem-solving, communication, and cross-functional collaboration skills.

Preferred Qualifications

• Experience with AI-powered content generation, content-as-code, personalization, or marketing technology platforms.
• Experience integrating with enterprise content management and marketing systems such as Workfront, Veeva Vault PromoMats, Adobe Experience Manager (AEM) Assets, or comparable platforms.
• Experience working in commercial pharmaceutical, life sciences, or other regulated content environments.
• Familiarity with content governance, traceability, and quality controls for enterprise marketing content.

Location and Time Zone Requirements

• Bay Area candidates are preferred, with the ability to work onsite 1-2 days per week.
• Candidates outside the Bay Area may be considered if they can consistently provide 4-6 hours of daily working overlap with Pacific Time.

#RTA

#LI-SK1

For workers in the United States, PrideGlobal and it's affiliates offers eligible employee's comprehensive healthcare coverage (medical, dental, and vision plans), supplemental coverage (accident insurance, critical illness insurance and hospital indemnity), 401(k)-retirement savings, life & disability insurance, an employee assistance program, legal support, pet insurance and employee discounts with preferred vendors.

Equal Employment Opportunity

PrideGlobal and it's affiliates are an equal opportunity employer. We do not discriminate on the basis of the race, religious creed, color, national origin, ancestry, physical disability, mental disability, reproductive health decision making, medical condition, genetic information, marital status, sex, gender, gender identity, gender expression, age, sexual orientation, veteran or military status, or any other characteristic protected by applicable federal, state, or local law.

Fair Chance Employment

PrideGlobal and it's affiliates are a Fair Chance employer. We consider all qualified applicants, including those with criminal histories, in a manner consistent with applicable state and local Fair Chance laws and ordinances, including, the California Fair Chance Act and all applicable local Fair Chance ordinances.

Accommodations

We are committed to providing reasonable accommodations to applicants and employees with disabilities. If you require a reasonable accommodation to participate in the application or interview process, or to perform the essential functions of this role, please contact us.

Only applicable for San Francisco Candidates: Under the San Francisco Lactation in the Workplace Ordinance, we will provide written notice of lactation accommodation rights, and this notice will automatically be given upon hiring, any inquiry of parental leave or lactation accommodation.

Only applicable for Kentucky positions: For this type of employment, state law requires a criminal record check as a condition of employment. This applies to direct care staff (Examples: RN, LPN, Nurse Aides, Therapists) referred to Kentucky nursing facilities, assisted living communities, or long-term care facilities, in accordance with KRS 216.793.