Platform Engineer - Reliability & Scale

LangChain(27 days ago)

RemoteFull TimeSenior$150,799 - $200,968 (estimated)Engineering

About this role

As a Platform Engineer - Reliability & Scale at LangChain, you will design and implement high-throughput, data-intensive systems for LangSmith and LangGraph, ensuring their scalability and reliability. Your responsibilities include building monitoring and automated recovery systems, debugging performance issues, and shaping platform strategy through technical decision-making. You will also participate in on-call rotations to address incidents and drive improvements with a focus on operability and automation. A strong background in cloud infrastructure, database management, and software engineering is essential for success in this role.

View Original Listing

Required Skills

System Architecture
Reliability Engineering
Incident Response
Performance Optimization
Database Management
Cloud Infrastructure
Containerization
Observability Tools
Software Engineering
Operational Practices

+4 more

About LangChain

www.langchain.com

LangChain is a leading platform for building and deploying reliable AI agents, providing both engineering tools and open-source frameworks for developers. It streamlines the agent development lifecycle by offering products such as LangChain, LangGraph, and LangSmith, which cater to different levels of control and complexity in agent engineering. LangChain's innovative platform is designed to support various AI models, facilitating quick iteration and integration while ensuring high performance. With robust observability and evaluation tools, LangChain empowers organizations to enhance their AI capabilities and improve operational efficiencies across diverse use cases.