Lead Openai Forward Deployed Engineer - Gps

Lead engineer responsible for deploying GenAI solutions into production for clients, leading engineering pods, architecting LLM applications, governing RAG pipelines, and defining evaluation frameworks. Requires hands-on experience with OpenAI technologies and leading project workstreams.

What you'd actually do

  1. Serve as the senior practitioner-leader embedded directly with our most strategic clients, leading forward-deployed engineering pods that develop and deploy GenAI solutions into production for Deloitte’s most strategic clients.
  2. Set technical direction, remove delivery blockers, and stay hands-on; designing, reviewing, and debugging systems with the team.
  3. Architect and oversee delivery of LLM-enabled applications including copilots, agentic workflows, assistants, and knowledge search experiences using one or more enterprise AI platforms (see Platform Requirements below)
  4. Govern end-to-end RAG pipeline design—including ingestion, chunking, embedding, vector retrieval, and hybrid search—ensuring production-grade quality and scalability.
  5. Define evaluation frameworks covering quality, hallucination risk, safety, latency, cost, and governance; ensure the pod meets agreed engineering quality bars to these standards.

Skills

Required

  • 10+ years of experience in software engineering, data engineering, data science, or analytics engineering
  • 1+ years of hands-on experience building and deploying GenAI/LLM-powered solutions in client or production environments
  • 1+ years of experience with OpenAI including hands on experience with one of the following key platform technologies; GPT-4o, Assistants API, Responses API, OpenAI Agents SDK
  • 1+ years of experience leading project workstreams/engagements and translating business problems into AI solutions
  • 1+ years of experience building reliable, maintainable, and well-documented code
  • Ability to travel 50%, on average
  • Must be legally authorized to work in the United States without the need for employer sponsorship
  • Ability to obtain and maintain a US government security clearance

Nice to have

  • Experience with cloud environments (AWS, Azure, and/or Google Cloud) and common platform services (storage, compute, IAM, networking)
  • Demonstrated ability to work directly alongside client technical teams and program stakeholders in fast-paced, ambiguous de

What the JD emphasized

  • leading forward-deployed engineering pods
  • deploy GenAI solutions into production
  • hands-on; designing, reviewing, and debugging systems
  • client-facing presence
  • building and deploying GenAI/LLM-powered solutions in client or production environments
  • hands on experience with one of the following key platform technologies; GPT-4o, Assistants API, Responses API, OpenAI Agents SDK
  • building reliable, maintainable, and well-documented code
  • Define evaluation frameworks covering quality, hallucination risk, safety, latency, cost, and governance

Other signals

  • Deploying GenAI solutions into production
  • Leading forward-deployed engineering pods
  • Architect and oversee delivery of LLM-enabled applications
  • Governing end-to-end RAG pipeline design
  • Define evaluation frameworks covering quality, hallucination risk, safety, latency, cost, and governance