Research Engineer, LangSmith Engine - Production AI

LangChain; New York, San Francisco (NY, CA); On-site; USD 180,000 - 240,000; Full time

Benefits offered by this job

Equity

Medical, dental, vision benefits

401(k) plan

Flexible vacation

Meals on in-office days in the US

Job summary

LangChain is hiring an experienced research engineer for the LangSmith Engine team in the US. You will study real agent failures, build benchmarks, run experiments to improve performance, and translate ideas into production improvements.

The role focuses on prompting, model selection, fine-tuning, and cost-aware system design. You will collaborate with production engineers, define technical direction, and mentor others while working on a production system with measurable improvements in latency,

Qualifications

• 4+ years of ML/AI research or closely related field.
• Master’s or Ph.D. in a relevant scientific field.
• Hands-on experience with LLMs and AI agents, including analyzing model behavior and improving real-world performance.
• Strong experience designing benchmarks, evaluations, and experiments for AI/ML systems.

Responsibilities

• Build and maintain benchmarks and evaluations that measure quality and efficiency of Engine agents on real-world tasks.
• Design and run experiments to improve agent performance across models, prompting, context, tools, orchestration, and strategies.
• Explore post-training and fine-tuning techniques to meaningfully improve capabilities, cost, or quality.
• Turn successful experiments into production improvements with engineers and researchers to measure impact.
• Help define the ML roadmap and mentor other engineers.

Skills

4+ years ML/AI research

LLMs & AI agents

Benchmarks & evaluations

Production impact

Strong technical leadership

Education

Master’s or PhD in a relevant field

Tools

LLMs

GPU infrastructure

Job description

LangChain is hiring an experienced research engineer for the LangSmith Engine team in the US. You will study real agent failures, build benchmarks, run experiments to improve performance, and translate ideas into production improvements.

The role focuses on prompting, model selection, fine-tuning, and cost-aware system design. You will collaborate with production engineers, define technical direction, and mentor others while working on a production system with measurable improvements in latency,