Base Salary
$185k - $240k/yr
Responsibilities
- Design, build, and operate high-throughput ingestion and trace-query systems on SmithDB.
- Develop monitoring, alerting, and automated recovery to keep ingestion pipelines resilient.
- Define API, SDK, and CLI standards, tooling, and CI for SDK generation across Python, TypeScript, Go, and Java.
- Build and maintain integrations for AI frameworks, agents, and tools.
- Debug performance bottlenecks, optimize database queries, and solve distributed-systems challenges.
- Participate in an on-call rotation focused on post-incident learning, automation, and prevention.
Requirements
- Hands-on experience designing and operating data-intensive platform systems at scale.
- Track record of building widely adopted CLIs, SDKs, or API standards.
- Production experience with PostgreSQL and Redis or other open-source datastores.
- Strong production-level backend software engineering experience with Go, Python, or TypeScript.
- Knowledge of cloud object storage, Kubernetes, containerized infrastructure, and GCP or AWS.
- Hands-on experience with observability stacks such as Datadog, Prometheus/Grafana, or OpenTelemetry.
- Experience building and operating production systems or developer-facing APIs is preferred.
- Strong experience with Java is preferred.
- Knowledge of columnar file and memory formats and OLAP databases is preferred.
- Experience in high-growth startups is preferred.
Benefits
- Medical, dental, and vision coverage
- Flexible vacation
- 401(k) plan
- Life insurance
- Meals on in-office days in the US
- Role based in NYC or San Francisco
Tech Stack
About LangChain
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. What began as widely adopted open-source tools has grown into a platform for building, evaluating, deploying, and operating agents at scale. LangChain provides the agent engineering platform and open source frameworks developers need to ship reliable agents fast. LangSmith offers observability, evaluation, and deployment for rapid iteration. Our open source frameworks, LangGraph, LangChain, and Deep Agents, help developers build agents with speed and granular control. LangSmith is trusted by leading AI teams at Zip, Vanta, Klarna, Workday, Linkedin, Cloudflare, and more.