Agent Reliability Engineer, GTM
LangChain · San Francisco, CA
About this role
**Agent Reliability Engineer, GTM** **About LangChain** We're building the foundation for agent engineering in the real world. Our mission is to make intelligent agents ubiquitous, helping developers move from prototypes to production-ready AI agents. We've raised $125M at Series B and serve 6,000+ LangSmith customers, including 5 of the Fortune 10. **About the Team** GTM Engineering builds the AI agents, systems, and automation that power our go-to-market operations. We partner across Sales, Marketing, Customer Success, and Support to identify high-leverage problems and build solutions that improve speed, quality, and scale. **The Role** You'll own the health, cost, performance, and business impact of the GTM Agent. You'll monitor production health, triage issues, run eval suites, track metrics, and build the feedback loops that keep the agent improving. You'll work with Python 3.11, FastAPI, LangGraph, DeepAgents, LangSmith, Supabase Postgres, BigQuery, and major LLM APIs. **What You'll Do** • Monitor production health and catch errors, slow runs, and failures before they're reported • Triage issues and fix small problems directly • Run weekly eval suites and turn bugs into regression tests • Track cost and latency by model, graph, and use case • Build business metrics showing agent ROI and impact • Develop monitoring and alerting on LangSmith **What You'll Bring** • Strong production Python and SQL skills • Real experience running LLM applications (tracing, evals, prompt mechanics) • SRE/production operations instincts (percentiles, SLOs, pattern recognition) • Healthy skepticism about metrics • Clear writing and interest in sharing what you learn • High agency and initiative **Nice to Haves** LangGraph/LangSmith experience, eval suite building, BigQuery/dbt, DevRel writing, GTM empathy **Compensation** $150,000 - $190,000 + equity, benefits (medical, dental, vision, 401k, flexible vacation)
Listing freshness
CronJobs last confirmed this listing 17h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.