2 months ago
Base Salary
$150k - $215k/yr
Responsibilities
- Advise enterprise customers on agent architecture, evaluation strategies, and production best practices.
- Co-build reliable production agents with customer engineering teams across the full Agent Development Lifecycle.
- Embed with customer organizations for extended engagements and ship agent systems alongside their engineers.
- Design orchestration patterns, evaluations, custom conversational UIs, and production deployments.
- Deliver applied AI work including post-training, supervised fine-tuning, harness engineering, trace mining, model selection, and evaluation methodology.
- Translate enterprise workflows into concrete software specifications and explain architectural tradeoffs to technical stakeholders.
Requirements
- 4+ years of software engineering experience with deep expertise in Python.
- 2+ years of hands-on experience building and shipping production agent systems.
- Strong client-facing communication skills and the ability to articulate architectural decisions to engineers, architects, and CTOs.
- Strong experience with LangChain, LangGraph, Deep Agents, or comparable frameworks, including multi-agent patterns and state management.
- Deep familiarity with evaluation methodologies for non-deterministic AI systems.
- Ability to work across advisory, co-building, and embedded delivery engagements.
- TypeScript or JavaScript experience is a plus.
- Experience with dataset curation and post-training techniques such as SFT, DPO, or RLHF on open-weight models is a nice-to-have.
- Experience with Axolotl, Unsloth, Hugging Face Transformers, or TRL is a nice-to-have.
- Experience with trace mining to drive continuous improvement loops is a nice-to-have.
Benefits
- Medical, dental, and vision coverage.
- Flexible vacation.
- 401(k) plan.
- Meals on in-office days in the US.
- Equity is included in the compensation package.
- Role is based in New York, New York.
Tech Stack
Categories
Forward Deployed
About LangChain
LangChain builds open-source frameworks and a commercial platform for developing, evaluating, deploying, and operating LLM-powered agents and applications. Its LangSmith suite provides observability, testing, deployment, and governance for enterprise AI workloads; customers include Nvidia, LinkedIn, Workday, and Bridgewater. Privately held and headquartered in San Francisco, the company was founded in 2022.