LangChain builds the foundation for agent engineering, helping developers move from prototypes to production-ready AI agents.
Platform includes LangSmith (Observability, Evaluation, Deployment, Fleet, Sandboxes), open source frameworks (LangChain, LangGraph, Deep Agents), and LangSmith Engine.
$125M raised at Series B from IVP, Sequoia, Benchmark, CapitalG, Sapphire Ventures.
About the team
The Infrastructure team builds and maintains the systems that power LangChain’s developer platform, including LangGraph Cloud and LangSmith.
Focuses on reliability, scalability, and developer productivity across the stack.
About the role
Hiring a Software Engineer to join the Infrastructure team and own developer productivity across LangGraph Cloud/Platform and LangSmith products.
Work closely with Infrastructure, Backend, and Frontend teams to ship with confidence across Kubernetes-based services, APIs, and UI flows.
Help pioneer quality practices specific to LLM applications, such as prompt regression testing and evaluation suites.
Responsibilities
Own test strategy end-to-end across APIs, services, UI, data, and infrastructure (Kubernetes, Terraform, Helm).
Stand up ephemeral test environments in Kubernetes for pull requests and release candidates.
Shift quality earlier in CI/CD pipelines (GitHub Actions) through parallelization, caching, deterministic seeds, flake tracking, and quality gates.
Build observability into testing workflows with rich failure artifacts such as logs, traces, and dashboards.
Establish performance and reliability baselines for critical paths, including SLIs, SLOs, and regression detection.
Partner on incident workflows.
Write documentation including test plans, playbooks, and contributor guidelines.
Requirements
3+ years of experience as a software engineer or infrastructure engineer.
Strong hands-on experience with Python and testing frameworks such as pytest.
Experience working with CI/CD systems (GitHub Actions preferred) and improving pipeline performance and reliability.
Solid understanding of API testing, mocking/stubbing, and data setup/teardown.
Comfort defining quality standards, writing test plans, and driving cross-team execution.
Nice to have
Experience with load and performance testing tools such as k6.
Familiarity with observability tooling such as Datadog or OpenTelemetry.
Experience testing services running on Kubernetes and containerized environments.
Basic infrastructure experience with Helm, Terraform, Kubernetes networking, or secrets management.
SQL fluency for validating data (Postgres, ClickHouse, BigQuery).
Familiarity with Go, Node, or React.
Conditions
In person 5 days/week in San Francisco, CA or New York, NY.
Annual salary range: $175,000 - $240,000 USD.
Benefits include medical, dental, and vision coverage, flexible vacation, a 401(k) plan, meals on in-office days in the US and more.