Infrastructure Engineer (LangGraph Platform)

About LangChain

LangChain was founded in early 2023 to help developers build context-aware reasoning applications. LangChain, open source software, is a framework that gives developers the building blocks to create production-ready applications with LLMs. LangSmith is our commercial, all-in-one SaaS platform that enables the end-to-end, development workflow for building LLM-powered apps. LangSmith is now trusted by the best teams building with LLMs, at companies such as Airbnb, ByteDance, Klarna, Google, Meta, Home Depot, and our 80+ paying enterprise customers.

Backed by some of the best venture capitalists, Benchmark and Sequoia, we have 10x’d our revenue last year and have big ambitions and are set up to build an enduring business.

About the role

In person 5 days/week in San Francisco, CA or New York, NY

We are seeking a highly motivated Infrastructure Engineer to join our LangGraph Platform team. This individual will be responsible for designing, implementing, and maintaining critical infrastructure components to ensure our platform is reliable, scalable, and secure. The ideal candidate has strong experience working with Kubernetes (K8s) and Terraform (Tf), is comfortable participating in on-call rotations and troubleshooting production issues, and can operate with a high degree of autonomy. Basic full-stack proficiency is a plus, but not a strict requirement. Some key responsibilities include:

• Architect, build, and maintain Kubernetes-based infrastructure to support LangGraph Cloud/Platform

• Ensure all infrastructure components adhere to best practices for security, scalability, and availability.

• Participate in on-call rotations to monitor systems, respond to alerts, and troubleshoot critical issues.

• Conduct root-cause analysis for production incidents, propose and implement fixes, and create post-incident documentation.

• Implement automated testing, monitoring, and health checks at the infrastructure layer.

• Exhibit a self-starter mentality; proactively identify areas for improvement and drive projects to completion with minimal guidance.

• Create and maintain comprehensive documentation for infrastructure architecture, deployment processes, and on-call procedures

• Bonus: Contribute to front-end codebases as needed, leveraging basic full-stack proficiency.

How to be successful in this role

• 5+ years of professional experience in infrastructure engineering or a related role.

• Strong proficiency in Kubernetes (K8s) for container orchestration and Terraform (Tf) for IaC.

• Hands-on experience troubleshooting production environments and participating in on-call rotations.

• Familiarity with cloud platforms (e.g., AWS, GCP, or Azure).

• Excellent problem-solving skills, with a track record of self-direction and initiative.

• Bonus: Basic understanding of full-stack development (e.g., Node.js, Python, React, etc.).

Compensation & Benefits

• Competitive salary and equity stake for role and stage of company. Commensurate with experience.

• Annual salary range: $145,000-$195,000 USD for Senior Engineers