1. Role description
Build and improve enterprise AI capabilities, including agent workflows, retrieval-augmented generation (RAG), and API integrations. Collaborate with business stakeholders and engineering to deliver reliable, secure, production-ready solutions across enterprise AI services and applications.
2. Skills
Core skills include Python and asynchronous API development, LangChain/LangGraph/LangSmith agent orchestration, Azure OpenAI, Azure AI Search, RAG, embeddings, and secure enterprise integrations such as the Microsoft Graph. Frontend experience with Next.js, React, and TypeScript is a nice to have, as are Cosmos DB/MongoDB and Redis.
3. Desired background
Demonstrated experience delivering production AI/LLM applications, particularly agentic workflows and RAG systems. Microsoft Azure experience is preferred; energy or utilities experience is a plus. Able to contribute to end-to-end feature delivery as part of a cross-functional team, including data integration and production deployment. Experienced in building secure, permission-aware enterprise integrations and using Git and CI/CD practices. Produces clear technical documentation and handovers, and can explain architecture and trade-offs to nontechnical stakeholders.
4. Timeline
- Target start: November 2, 2026, or the earliest practical date after selection, onboarding, and access approval.
- Expected duration: Six months initially; any extension subject to funding and delivery needs.
5. Headcount
One full-time AI Engineer, approximately 40 hours per week, subject to contract.
6. Location
US (remote)