Senior Backend Engineer, LangSmith Deployments

LangChain, Inc.

Job Overview

Location

San Francisco, California, USA

Job Type

Full-time

Full Job Description

📋 Description

• Join LangChain, Inc. as a Senior Backend Engineer, focusing on the cutting-edge LangSmith Deployments platform, the engine powering the next generation of intelligent agents. Our mission at LangChain is to make intelligent agents ubiquitous, and you will be instrumental in building the robust, scalable infrastructure required to achieve this vision. This role is deeply technical, requiring a strong backend foundation coupled with a keen understanding of distributed systems and modern DevOps practices.
• LangSmith Deployments is not just another backend service; it's a purpose-built runtime designed for the unique challenges of AI agents. Unlike traditional web applications, agents operate for extended durations, engage in complex asynchronous collaborations with both humans and other agents, and must maintain state and resilience through inevitable failures. Your work will directly contribute to a system that offers durable checkpointing, fault-tolerant orchestration, and seamless horizontal scaling, capable of deployment across both cloud and self-hosted environments.
• As a Senior Backend Engineer on this team, you will be at the forefront of designing and implementing core components of this sophisticated runtime. This includes architecting distributed queue and worker systems engineered to handle the concurrency demands of agent execution, manage background tasks efficiently, and facilitate multi-agent coordination within a horizontally scalable infrastructure. Your contributions will ensure that our platform can support a vast number of agents operating simultaneously and reliably.
• You will take ownership of our core data infrastructure, a critical element for agent reliability. This involves designing and implementing solutions for state persistence, ensuring atomic job claiming to prevent race conditions, managing persistent connections, and architecting for graceful schema evolution as the platform grows and requirements change. The integrity and performance of this data layer are paramount to the success of LangSmith Deployments.
• Collaboration is key in our small, agile team. You will actively participate in architectural decision-making processes, contributing your expertise to ensure that all solutions are not only scalable but also exceptionally robust and maintainable. This is an opportunity to shape the technical direction of a foundational product.
• A significant aspect of this role involves shipping and refining resumable streaming infrastructure. This capability is vital for agent applications, allowing clients to disconnect and reconnect mid-execution without any loss of state, ensuring a seamless and uninterrupted user experience even in the face of network instability or user-initiated interruptions.
• You will be responsible for instrumenting and meticulously monitoring our production systems. This includes implementing comprehensive tracing, collecting key metrics, and setting up effective alerting mechanisms to proactively identify and address potential issues, thereby maintaining the overall health and performance of the platform.
• This role includes participation in on-call rotations, where you will take ownership of incident response for the runtime. This hands-on experience with production issues is invaluable for understanding system behavior under stress and driving improvements.
• Creating and maintaining high-quality technical documentation is a crucial part of the role. This includes detailed system design documents and operational runbooks that empower the team and future engineers to understand, operate, and maintain the LangSmith Deployments runtime effectively.
• You will also have the opportunity to contribute to and extend our open-source LangGraph framework. LangGraph is a vital tool used by thousands of developers worldwide to build sophisticated agent applications, and your contributions will directly impact the broader AI developer community.
• This role requires an in-person presence, 5 days a week, either in our San Francisco, CA or New York, NY office, fostering close collaboration and team synergy.

🎯 Requirements

• 4+ years of professional backend engineering experience.
• Strong proficiency in Go and/or Python.
• Experience with distributed systems, including consensus mechanisms, queueing, state machines, and/or workflow orchestration.
• Experience with scaling and sharding databases in high throughput environments.
• Familiarity with Kubernetes, infrastructure-as-code (e.g., Terraform), and at least one major cloud platform (AWS, GCP, Azure).
• Strong communication skills and ability to work cross-functionally on a small, fast-paced team.

🏖️ Benefits

• Competitive compensation package including base salary and meaningful equity.
• Comprehensive health and dental coverage.
• Flexible vacation policy.
• 401(k) plan.
• Life insurance.
• Opportunity to work on a foundational product in the rapidly growing AI agent space.
• Collaborative and innovative team environment.

Skills & Technologies

Python

Kubernetes

Terraform

Backend

Senior

Onsite

$175k-0k

Ready to Apply?

Apply Externally

You will be redirected to an external site to apply.

LangChain, Inc.

Visit Website

About LangChain, Inc.

LangChain, Inc. provides open-source software libraries and cloud services for building applications that integrate large language models with external data sources and workflows. Its tools help developers create retrieval-augmented generation systems, manage prompts, chain model calls, and monitor performance in production environments. The company was founded in 2023 and is headquartered in San Francisco, California.

View Company Profile