Production AI Reliability Engineer - GTM Agents

LangChain, Inc.; San Francisco, Northern (CA, KY); Hybrid; USD 150,000 - 190,000; Full time

Benefits offered by this job

Medical, dental, vision coverage

401(k) plan

Meals on in-office days in the US

Job summary

LangChain, Inc. is hiring for a production-focused role overseeing GTM AI agents. You will manage health, cost, and performance of the GTM Agent, and operate LangSmith and related tools.

The role spans Python 3.x, SQL, and AI model orchestration across LangGraph, DeepAgents, and OpenAI models, with interfaces to Slack and Next.js surfaces. You will monitor production health, triage issues, run eval suites, track costs, and build business metrics to demonstrate ROI.

Qualifications

• Strong production Python and SQL skills with experience in traces and warehouse tables.
• Hands-on experience running LLM applications including tracing, evals, and caching.
• SRE/production operations instincts: feel for SLOs and noise vs. signal.
• Analytical mindset to assess metrics and publish meaningful numbers.
• Clear writing and willingness to share learnings.

Responsibilities

• Monitor production health across graphs; detect errors and expensive runs early.
• Triaging issues from Slack, tickets, and reports; fix small items and route others.
• Run weekly eval suite; investigate failures and turn bugs into regression tests.
• Track cost and latency by model and use case; recommend changes.
• Track usage per rep/feature and own weekly health reports.
• Build business metrics showing agent value from key outcomes.
• Develop monitoring and alerting for LangSmith and document how we run our agent.

Skills

Python

SQL

LLM applications

SRE

Metrics & data

Writing

Initiative

Tools

LangSmith

LangGraph

BigQuery

Job description

LangChain, Inc. is hiring for a production-focused role overseeing GTM AI agents. You will manage health, cost, and performance of the GTM Agent, and operate LangSmith and related tools.

The role spans Python 3.x, SQL, and AI model orchestration across LangGraph, DeepAgents, and OpenAI models, with interfaces to Slack and Next.js surfaces. You will monitor production health, triage issues, run eval suites, track costs, and build business metrics to demonstrate ROI.