About the job
About Us:
At LangChain, we are dedicated to making intelligent agents a fundamental part of everyday technology. Our platform serves as a robust foundation for agent engineering in real-world applications, empowering developers to transition from initial prototypes to production-ready AI agents that are dependable for teams. Starting as widely embraced open-source tools, we have evolved into a comprehensive platform for building, evaluating, deploying, and managing agents on a large scale.
Our offerings, including LangChain, LangGraph, LangSmith, and Agent Builder, are trusted by teams delivering real AI products across both startups and major corporations. Millions of developers utilize LangChain to enhance AI capabilities at companies such as Replit, Clay, Coinbase, Workday, Lyft, Cloudflare, Harvey, Rippling, Vanta, and 35% of the Fortune 500.
With $125M raised in Series B funding from reputable investors like IVP, Sequoia, Benchmark, CapitalG, and Sapphire Ventures, we are poised for continued growth and innovation. Each team member plays a crucial role in shaping the technologies we develop and the collaborative culture we foster at LangChain.
About the Role:
This is an in-office position requiring presence in San Francisco, Boston, or New York City five days a week.
We are seeking a Senior Backend Engineer to join our team. In this role, you will be responsible for developing the backend systems that drive LangChain’s observability and evaluations platform. Your work will focus on core services that enable developers to monitor and assess their AI applications on a large scale. While your primary responsibilities will involve backend feature development, experience with full-stack or frontend engineering, performance optimization, and troubleshooting production issues will be highly beneficial.
Key Responsibilities:
Design, develop, and maintain backend services and APIs to facilitate LangSmith’s tracing, monitoring, and evaluation workflows.
Collaborate on architectural decisions to ensure systems are both high-performing and maintainable.
Optimize storage and query performance for high-volume observability and evaluation data.
Ensure system reliability with robust testing, monitoring, and alerting practices.
Diagnose and resolve production issues, conducting root-cause analysis and implementing lasting solutions.
Produce and maintain comprehensive technical documentation, including system design and API references.
