Senior Backend Engineer, AI Observability & Evals

AItoolnavio; New York (NY); On-site; USD 180,000 - 240,000; Full time

Benefits offered by this job

Medical coverage

Dental coverage

Vision coverage

401(k) plan

Flexible vacation

In-office meals (US)

Job summary

LangChain is seeking a Senior Backend Engineer in the US to build the backend systems powering LangSmith's observability, evaluation, and production reliability of AI systems. You will work on core services that allow developers to monitor and evaluate their AI applications at scale.

While the focus is on backend feature development, familiarity with full-stack or frontend engineering, performance tuning, and debugging production issues would be extremely valuable.

Qualifications

• 5+ years of professional backend experience on complex products.
• Proficiency in Python or Go.
• Strong API design and reliable data services.
• Experience with high-throughput or mission-critical systems.
• Ability to optimize backend services for performance and reliability.
• Experience with Postgres, Redis, ClickHouse, and cloud platforms (AWS, GCP, Azure).
• Strong cross-functional collaboration and communication.
• Customer-centric ownership mentality.

Responsibilities

• Design, develop, and maintain backend services and APIs.
• Collaborate on architectural decisions for performance and maintainability.
• Optimize storage and query performance for large observability data.
• Ensure reliability with testing, monitoring, and alerting.
• Troubleshoot production issues and implement long-term fixes.
• Create and maintain system documentation including API references.
• Work with frontend, product, and design teams on new features.

Skills

Years of backend experience

Python

Go

API design

High-throughput systems

Databases (Postgres, Redis, ClickHouse

Cloud platforms (AWS, GCP, Azure)

Communication

Tools

Postgres

Redis

ClickHouse

Job description

LangChain is seeking a Senior Backend Engineer in the US to build the backend systems powering LangSmith's observability, evaluation, and production reliability of AI systems. You will work on core services that allow developers to monitor and evaluate their AI applications at scale.

While the focus is on backend feature development, familiarity with full-stack or frontend engineering, performance tuning, and debugging production issues would be extremely valuable.