Software Engineer, Agent Systems (GTM Engineering)
About this role
Monitoring production health across every graph, catching errors, slow runs, expensive runs, and silent failures keeps the systems running smoothly day to day. This engineer owns the health, cost, performance, and business impact of the GTM Agent System while building feedback loops for continuous improvement.
Operating within the GTM Engineering team at LangChain, the person in this role builds AI agents, systems, and automation powering go-to-market functions like Sales, Marketing, and Customer Success. Because the team builds the platform they run on, the engineer operates the agent on LangSmith and turns that practice into a reference story for enterprise customers.
Success in this role requires a candidate with strong production Python and SQL skills, real experience running LLM applications, and SRE or production operations instincts. High agency and an ability to notice what is missing are essential for taking initiative and building solutions that improve speed, quality, and scale across the organization.
What you will do
- Monitor production health across every graph to catch errors, slow runs, expensive runs, and silent failures before reps report them.
- Triage incoming issues from Slack, tickets, and rep reports by fixing small problems directly and routing others to the appropriate owner.
- Run the weekly evaluation suite, investigate failures, and turn real production bugs into permanent regression tests.
- Track cost and latency by model, graph, use case, and role while recommending concrete changes to model choice, reasoning effort, and caching.
- Track usage and adoption per rep and per feature to own the weekly health report used by the team.
- Build business metrics that demonstrate the agent's value to leadership, covering reply rates, meetings booked, hours reclaimed, and ROI.
- Build internal monitoring and alerting on LangSmith and write the story of how the team runs its own agent for customers.
What you need
- Demonstrate strong production experience in Python and SQL with comfort working in traces, logs, and warehouse tables.
- Bring real experience running large language model applications, including tracing, evaluations, prompts, and cache mechanics.
- Apply site reliability engineering or production operations instincts covering percentiles, service level objectives, and pattern separation.
- Maintain a healthy skepticism about metrics by verifying what numbers actually count before publication.
- Possess clear writing skills and a demonstrated interest in publishing lessons learned.
- Exercise high agency by noticing missing elements and taking initiative to build them.
Nice to have
- LangGraph or LangSmith experience
- Experience building an eval suite from scratch
- BigQuery or dbt
- Prior DevRel-adjacent writing
- Empathy for sales and go-to-market users
Benefits
- Medical, dental, and vision coverage
- Flexible vacation
- 401(k) plan
- Meals on in-office days in the US
Skills and tech stack
Questions candidates ask
What is the salary range for this role?
The salary range for this position is $150,000 to $190,000. Actual compensation will vary based on role, level, and location.
What tools and technologies will I use?
You will work across Python 3.11, FastAPI, LangGraph, DeepAgents, LangSmith, Supabase Postgres, BigQuery, Anthropic and OpenAI models, and Slack and Next.js surfaces.
What benefits are provided?
Benefits include medical, dental, and vision coverage, flexible vacation, a 401(k) plan, and meals on in-office days in the US. Team members in the EU, UK, and APAC receive locally competitive benefits aligned with regional norms and regulations.