Software Engineering Manager, AI Observability & Evals Platform (New York, NY)

present of AI; New York (NY); On-site; USD 180,000 - 260,000; Full time

Job summary

LangChain seeks an Software Engineering Manager for AI Observability & Evals Platform in New York, NY. You will lead the LangSmith engineering team, mentor engineers, and define the technical direction while continuing to contribute code in Go, Python, and TypeScript.

You will design and scale data-intensive systems, work closely with product and customers to ship reliable, high-quality observability tools for LLM apps, and drive architectural decisions that keep the platform dependable at scale.

Qualifications

• Experience leading teams shipping full-stack products.
• Strong knowledge of Postgres, Redis and ClickHouse.
• Designs systems that handle large volumes of data.
• Hands-on engineering manager who still writes production code.

Responsibilities

• Lead the LangSmith observability and eval platform engineering team.
• Grow and mentor engineers, set technical direction.
• Own architecture for high-throughput data processing.
• Write code in Go, Python and TypeScript as needed.

Skills

Go

Python

TypeScript

Leadership

Tools

PostgreSQL

Redis

ClickHouse

Job description

Software Engineering Manager, AI Observability & Evals Platform (New York, NY)

This is a hands-on engineering manager role leading the team behind LangSmith, the observability and evaluation product for LLM apps. The work covers growing and mentoring engineers, setting technical direction, and still writing code in Go, Python and TypeScript. A strong candidate has led teams shipping full-stack products, knows Postgres, Redis and ClickHouse, and has designed systems that handle large volumes of data.

How it fits the AI era

AI agents fail in unpredictable ways, so tracing, testing and monitoring them is becoming a core need for any team that ships them. Tools can now help analyze traces and suggest fixes, which speeds up the work of understanding what an agent did. What stays human is deciding what good quality looks like, setting priorities with customers, and keeping a platform dependable at scale.

How it builds AI experience

Someone in this role works close to how real companies build and run agents in production, since the product serves teams doing exactly that. It also offers a view into evaluation methods and autonomous improvement features as they take shape. To prepare, build a small LLM app, trace it, and write evaluations for it using LangChain or LangGraph, then explore LangSmith's observability and evaluation features.

Worth showing

• Leading full-stack engineering teams
• High-throughput data system design
• ClickHouse and Postgres depth
• Customer-driven product shipping

This is our own read, written from the employer's posting and the company's Spotlight. The employer's posting is the source of truth for the role.

About LangChain

LangChain provides an open agent engineering platform and open source frameworks for building, testing, deploying, monitoring, and governing AI agents, per the company.