Deployed Engineer, Professional Services (San Francisco)
About this role
Translating vague enterprise workflows into concrete software specifications forms the core of daily operations in this customer-facing role. Team members advise on agent architecture, review evaluation strategies, and co-build solutions across the full agent development lifecycle alongside enterprise engineering clients. Sometimes this involves spending a week designing a customer architecture or embedding inside their team for an extended engagement to ship agent systems directly.
LangChain builds the foundation for agent engineering through open-source frameworks and a platform for evaluating, deploying, and operating agents at scale. The professional services team bridges the gap between these tools and real-world enterprise deployments, helping organizations move from prototypes to production-ready AI agents. Ideal candidates bring practical experience building real AI systems for production and can defend technical tradeoffs effectively.
What you will do
- Advise enterprise clients on agent architecture design, evaluation strategies, and production best practices.
- Co-build applications with customer engineering teams across the entire agent development lifecycle in outcome-scoped engagements.
- Serve as an embedded deployed engineer inside customer organizations to ship agent systems directly.
- Design orchestration patterns, custom conversational UIs, and production deployments.
- Apply post-training techniques, supervised fine-tuning, harness engineering, trace mining, and model selection methodologies.
What you need
- Bring four or more years of software engineering experience featuring deep expertise in Python.
- Possess two or more years of hands-on experience building and shipping production agent systems.
- Demonstrate strong client-facing communication skills to articulate architectural decisions to technical stakeholders such as engineers and CTOs.
- Show strong experience with LangChain, LangGraph, Deep Agents, or comparable frameworks including multi-agent patterns and state management.
- Maintain familiarity with designing and implementing evaluation methodologies for non-deterministic AI systems.
- Remain comfortable operating across the full spectrum from advisory consulting to embedded delivery.
- Agree to travel up to twenty percent of the time.
Nice to have
- Exposure to dataset curation and post-training techniques on open-weight models using tools like Axolotl, Unsloth, Hugging Face transformers, or TRL.
- Experience with trace mining to drive continuous improvement loops.
Benefits
- Medical, dental, and vision coverage
- Flexible vacation
- 401(k) plan
- Meals on in-office days in the US
Skills and tech stack
Questions candidates ask
Where is the role located?
The position is based in San Francisco, CA. The role also requires willingness to travel up to 20% of the time.
What is the compensation range?
The base salary ranges from $150,000 to $215,000. Compensation also includes meaningful equity, benefits, and perks.
What tools and frameworks will I use?
The tech stack involves Python, TypeScript, JavaScript, LangChain, LangGraph, Deep Agents, and LangSmith. Additional tools like Axolotl, Unsloth, and Hugging Face transformers are nice to have.
What does the team do?
The professional services team works directly with enterprise customers to build reliable, production agents. Team members translate vague enterprise workflows into concrete software specs and guide engineering teams through the resulting solution.