LangChain
AI Engineer, Enablement
About this role
LangChain seeks an AI Engineer for their Enablement team to design and deliver technical training on agent engineering and the LangSmith platform. You'll create workshops, tutorials, and reference implementations while building internal tools to scale the enablement function, serving enterprise customers who depend on LangChain in production.
What you'll do
- Design and deliver hands-on workshops that build product fluency with LangChain, LangGraph, and LangSmith
- Create scalable enablement assets including tutorials, reference implementations, and best-practice guides
- Provide technical guidance and office hours to customers debugging agent systems
- Build internal agents and tools that streamline Enablement team operations and processes
- Gather and communicate customer friction points and feature requests to Product and Engineering teams
- Stay current on agent engineering practices and incorporate learnings into training materials
What they're looking for
- LLM and agent application development (3+ years)
- Agent architecture and evaluation strategy design
- Python programming and live code debugging
- Technical workshop design and delivery
- Technical writing and documentation
- Customer-facing communication and presentation skills
- Independent project management and multi-stakeholder engagement
- Cloud environments and containerization (AWS, GCP, Azure)
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
LangChain
LangChain builds platforms and frameworks for developing, deploying, and observing production AI agents at enterprise scale, including LangSmith for AI observability and evaluation. The company is hiring Deployed Engineers to work directly with enterprise customers on agent implementation and operations, as well as Fullstack Engineers to build features across its platform stack.
- Website
- langchain.com
Likely interview questions
- Describe a complex agent system you've built—what tradeoffs did you make in its architecture and why?
- Tell us about a time you taught technical concepts to a diverse audience; how did you handle varying skill levels?