# Agent Reliability Engineer, GTM Engineering

Hiring organization: [LangChain](https://career.thegoodapps.co/organizations/langchain)

Canonical page: https://career.thegoodapps.co/jobs/d62ca949-0160-4826-a370-d792ef26bc4c

Listed on LangChain's own careers site. Applications go to them directly.

- Employment type: full time
- Location: San Francisco, CA
- Salary: 150000 – 190000 USD per year

## Summary

You'll own the health and reliability of LangChain's production AI agent that supports the go-to-market team, monitoring its performance, costs, and business impact while building the feedback loops and monitoring systems that keep it improving. This role suits engineers with strong production Python and SQL skills, real experience running LLM applications, and SRE instincts who want to both operate a complex system and evangelize the practices they build.

_Our summary, not LangChain's wording._

## Skills named

FastAPI, Google BigQuery, LangGraph, Next.js, OpenAI, Python, Slack, SQL, Supabase

## Required

- Production Python and SQL experience
- Experience running LLM applications including tracing and evals
- SRE or production operations background with understanding of percentiles and SLOs
- Ability to verify metrics and separate noise from real patterns
- Clear writing skills and interest in sharing learnings

## Nice to have

- LangGraph or LangSmith experience
- Experience building an eval suite from scratch
- BigQuery or dbt
- DevRel-adjacent writing experience
- Familiarity with sales and go-to-market workflows

Apply on LangChain's site: https://jobs.ashbyhq.com/langchain/eadd2a71-47fc-483b-948f-4b2384f7f93f/application