Senior Backend Software Engineer, AI Observability & Evals Platform (LangSmith)
About this role
Engineers who thrive in fast-paced environments focused on high-scale data handling will find a strong fit building the backend systems for LangChain's observability and evaluations platform, LangSmith. The team is responsible for the core infrastructure that enables developers to monitor, evaluate, and maintain production AI applications, handling massive volumes of tracing and evaluation data.
Daily responsibilities center on designing APIs, optimizing storage and query performance, and scaling backend services to support thousands of active customers. Candidates who enjoy tackling complex performance bottlenecks, working closely with cross-functional product teams, and taking full ownership of mission-critical services will do well in this Boston-based role.
What you will do
- Design, build, and maintain scalable backend services and APIs that power tracing, monitoring, and evaluation workflows.
- Contribute to architectural decisions to maintain high performance and long-term system maintainability.
- Optimize storage layers and query execution for high-volume observability datasets.
- Maintain system reliability through comprehensive testing, proactive monitoring, and alerting configurations.
- Investigate production incidents, conduct thorough root-cause analysis, and deploy durable fixes.
- Produce and update technical documentation, covering system architecture and API references.
- Partner with full-stack engineers, product managers, and designers to deliver new platform features.
What you need
- Bring at least four years of professional backend engineering experience building complex products.
- Demonstrate proficiency in modern backend languages and frameworks, with a preference for Python or Go.
- Possess a strong grasp of API design principles and the construction of reliable data services.
- Show past experience working on high-throughput, mission-critical production systems.
- Exhibit a proven ability to tune backend services for optimal performance and uptime.
- Maintain strong communication skills to facilitate effective cross-functional collaboration.
Nice to have
- Experience with database systems including Postgres, Redis, and Clickhouse
- Familiarity with cloud platforms such as AWS, GCP, and Azure
- Background in full-stack or frontend engineering
- Skills in performance tuning and debugging production issues
Benefits
- Medical, dental, and vision coverage
- Flexible vacation
- 401(k) plan
- Meals on in-office days in the US
Skills and tech stack
Questions candidates ask
Where is the job located?
This role is based onsite in Boston, MA.
What is the salary range for this position?
The annual salary range is $180,000 to $240,000.
What technologies will I be working with?
The tech stack involves backend development using languages like Python and Go, along with databases and cloud platforms.
What does the team actually own?
The LangSmith team owns LangChain's core platform for observability, evaluation, and production reliability end-to-end.