LangChain
Deployed Engineer, Professional Services (San Francisco)
About this role
Join LangChain's Professional Services team as a Deployed Engineer to work directly with enterprise customers building production-ready AI agent systems. You'll advise on architecture, co-build solutions, and embed within customer teams to ship reliable agent systems end-to-end using LangChain's platform.
What you'll do
- Design agent architectures and evaluate strategies for enterprise customers
- Co-build agent systems across the full development lifecycle with customer engineering teams
- Embed as an extended team member within customer organizations to deliver agent solutions
- Implement evaluation methodologies and production deployment strategies for AI systems
- Guide technical stakeholders through architectural decisions and best practices
- Apply post-training and fine-tuning techniques to optimize model performance
What they're looking for
- Python (deep expertise)
- TypeScript/JavaScript
- LangChain/LangGraph/Deep Agents frameworks
- Agent architecture and multi-agent patterns
- AI system evaluation methodology design
- Production deployment and operations
- Client-facing communication and stakeholder management
- Post-training techniques (SFT, DPO, RLHF)
Benefits
- Medical, dental, and vision coverage
- Flexible vacation policy
- 401(k) plan
- Meals on in-office days
- Equity compensation
- Competitive base salary
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
- Walk us through a production agent system you built—what were the key architectural decisions and trade-offs?
- How do you approach evaluating non-deterministic AI systems, and what methodologies have you found most effective?