LLM Framework · San Francisco
At LangChain, our mission is to make intelligent agents ubiquitous. We build the foundation for agent engineering in the real world, helping developers move from prototypes to production-ready AI agents that teams can rely on. We began as widely adopted open-source tools and have grown to also offer a platform for building, evaluating, deploying, and operating agents at scale.
With $125M raised at Series B from IVP, Sequoia, Benchmark, CapitalG, and Sapphire Ventures, we’re at a stage where we’re continuing to develop new products, growth is accelerating, and all team members have meaningful impact on what we build and how we work together. LangChain is a place where your contributions can shape how this technology shows up in the real world.
Today, LangChain, LangGraph, LangSmith, and Fleet are used by teams shipping real AI products across startups and large enterprises. Millions of developers trust LangChain to power AI teams at companies like Replit, Clay, Coinbase, Workday, Lyft, Cloudflare, Harvey, Rippling, Vanta, and 35% of the Fortune 500.
About the Team
The Infrastructure team builds and maintains the systems that power LangChain’s developer platform, including LangGraph Cloud and LangSmith. The team focuses on reliability, scalability, and developer productivity across the stack, working closely with backend, frontend, and platform engineers to ensure services are deployed, tested, and operated with confidence.
About the Role
We’re hiring a Software Engineer to join the Infrastructure team and own developer productivity across our LangGraph Cloud/Platform and LangSmith products. You’ll work closely with Infrastructure, Backend, and Frontend teams to ship with confidence across Kubernetes-based services, APIs, and UI flows. You’ll also help pioneer quality practices specific to LLM applications, such as prompt regression testing and evaluation suites.
Location: In person 5 days/week in San Francisco, CA or New York, NY
What You'll Do
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; seed test data and run hermetic test suites
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 by reproducing issues, adding targeted regression tests, and improving runbooks and postmortems
Write documentation including test plans, playbooks, and contributor guidelines for writing high-quality tests
Example projects you might own
A pull-request ephemeral end-to-end testing harness that deploys a minimal LangSmith stack in CI and runs Playwright and API suites against seeded tenants
A k6 performance scenario that simulates multi-tenant traffic and surfaces p95/p99 latency regressions per release
A flake-budget system that automatically quarantines flaky tests, opens issues with artifacts, and tracks time-to-deflake
What You'll Bring
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 for targeted white-box tests and improving system testability
Compensation
Annual salary range: $160,000- $225,000 USD
Compensation Philosophy:
We offer competitive compensation that includes base salary, variable compensation for relevant roles, meaningful equity, benefits, and perks. Actual compensation and offerings will vary based on role, level, and location. Team members in the EU, UK, and APAC receive locally competitive benefits aligned with regional norms and regulations.
Benefits include medical, dental, and vision coverage, flexible vacation, a 401(k) plan, meals on in-office days in the US and more.