The opportunity
The LangSmith team owns and builds LangChain's core platform for observability, evaluation, and production reliability of AI systems. From tracing and annotation to run rules, evaluations, and beyond, they own this end-to-end.
What you'll do
Lead architectural decisions across our Go, Python, and TypeScript stack,: ensuring systems are performant, maintainable, and built to scale
Work across the full stack, owning features end-to-end from backend services: and APIs through to frontend product experiences
Drive tracing, monitoring, and evaluation workflows at scale, with a focus on: reliability and query performance across high-volume data
Help shape the product roadmap by partnering closely with product and design — not just executing on it
Set engineering standards for the team: define patterns, lead code reviews, and establish the foundations others build on
Mentor and grow engineers at all levels through code review, design feedback,: pairing, and ongoing technical guidance
What they're looking for
- Drive projects from ambiguity to delivery while maintaining high engineering: standards and aggressive timelines
- Troubleshoot and resolve production issues with a root-cause mindset, and implement durable fixes
- Ensure system reliability through strong testing, monitoring, and alerting practices
- Create and maintain technical documentation, including system design docs and API references
