LangChain
Deployed Engineer (Early Career-NYC)
About this role
Join LangChain as a Deployed Engineer working directly with Fortune 500 companies to architect, build, and operate production AI agents. You'll bridge engineering and go-to-market, turning customer prototypes into reliable systems using the LangChain platform while providing technical leadership across the full deployment lifecycle.
What you'll do
- Co-architect and build production AI agents alongside customer engineering teams
- Own technical wins in pre-sales by designing POCs and guiding evaluations
- Deploy and operate agent applications including conversational and research agents
- Advise customers on architecture, best practices, and roadmap decisions post-deployment
- Conduct technical demos, trainings, and workshops for developer audiences
- Travel to customer sites (~40%) for hands-on support and technical engagement
What they're looking for
- Python and JavaScript
- Agent-based and LLM application design
- Systems architecture fundamentals
- Customer collaboration and communication
- Technical troubleshooting and problem-solving
- Multi-step workflow orchestration
- Production deployment and operations
- Solutions architecture
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
- Can you walk through a complex LLM-powered application you've designed, including how you handled failure modes and orchestration?
- Tell us about a time you had to explain a difficult technical tradeoff to a non-technical stakeholder—how did you approach it?