LLM Framework · San Francisco
At LangChain, our mission is to make intelligent agents ubiquitous. We build the foundation for agent engineering in the real world, helping developers move from prototypes to production-ready AI agents that teams can rely on. We began as widely adopted open-source tools and have grown to also offer a platform for building, evaluating, deploying, and operating agents at scale.
With $125M raised at Series B from IVP, Sequoia, Benchmark, CapitalG, and Sapphire Ventures, we’re at a stage where we’re continuing to develop new products, growth is accelerating, and all team members have meaningful impact on what we build and how we work together. LangChain is a place where your contributions can shape how this technology shows up in the real world.
Today, our platform includes LangSmith (Observability, Evaluation, Deployment, Fleet, and Sandboxes), our open source frameworks (LangChain, LangGraph, and Deep Agents), and the newly launched LangSmith Engine for autonomous agent improvement. We have 100M+ monthly open source downloads, 6,000+ active LangSmith customers, and 5 of the Fortune 10 use LangSmith in production (+ 35% of the Fortune 500 overall), including teams at Klarna, Clay, Coinbase, Workday, Lyft, Cloudflare, Harvey, Rippling, Vanta, LinkedIn, Monday.com, Nvidia, and Bridgewater.
About the team
SmithDB is LangChain's internal database team. We're building a storage and query layer purpose-built for AI observability and evaluation. Within six months we went from idea to a production system that offers industry leading performance and scalability for agent observability data. We're a small, fast team of systems engineers tackling genuinely hard problems: storage layout, query execution, compaction, and scaling toward trillions of agenbt traces. We develop in Rust, run on Kubernetes, and integrate tightly with S3/GCS/Azure Blob. There are no legacy constraints; this is a greenfield system with real production load and ambitious engineering goals.
About the role
We're looking for a hands-on Engineering Manager to lead the SmithDB team. This is not a pure people-management role. You'll write production code, review PRs at the systems level, make architectural calls, and be in the weeds alongside your engineers. At the same time, you'll own team health, hiring, technical roadmap, and coordination with the broader LangSmith platform. The ideal candidate has deep systems or database engineering experience and genuinely prefers to stay technical while growing a team.
What you'll do
Write and review production Rust code across ingestion, query execution, and storage layers
Lead architectural decisions on storage format, compaction, indexing, and query planning
Drive performance investigations using memory and CPU profiling tools; own the path from profiling to shipped fix
Design and harden the distributed deployment of SmithDB services on Kubernetes (multi-tenant, high-throughput, low-latency)
Contribute to cloud object store integrations (S3, GCS, Azure Blob) and set the standard for how SmithDB manages data at rest and in flight
Build and maintain observability for the engine itself: metrics, tracing, debug tooling
Manage a small but growing team of systems engineers: set goals, run 1:1s, provide technical mentorship, and grow careers
Own the SmithDB technical roadmap in partnership with LangSmith product and engineering leadership
Communicate progress, risks, and tradeoffs clearly to the broader organization: you write concise, decision-ready updates
What you'll bring
7+ years in systems or database engineering, with at least 2 years in a technical lead or engineering management role
Production Rust experience — you can write it, review it, and have opinions on how to structure it at scale
Deep understanding of database or storage engine internals: query execution, storage layouts, indexing, compaction
Proficiency in systems performance analysis: memory allocators, CPU hotspots, lock contention, async runtimes (Tokio)
Experience deploying and operating distributed services on Kubernetes in a production, multi-tenant environment
Familiarity with cloud object storage (S3-compatible APIs, consistency models, cost/performance tradeoffs)
Proven track record of managing engineers — you can recruit, retain, and level-up a team without losing your technical edge
Nice-to-have:
Experience building or contributing to columnar storage formats (Parquet, Arrow), OLAP query engines, or time-series stores
Background in observability infrastructure or tracing pipelines (OpenTelemetry, ClickHouse, Prometheus)
Experience scaling a system from early-stage to hundreds of billions / trillions of records
Compensation
Salary Range: $215,000-$260,000 USD
Compensation Philosophy:
We offer competitive compensation that includes base salary, variable compensation for relevant roles, meaningful equity, benefits, and perks. Actual compensation and offerings will vary based on role, level, and location. Team members in the EU, UK, and APAC receive locally competitive benefits aligned with regional norms and regulations.
Benefits include medical, dental, and vision coverage, flexible vacation, a 401(k) plan, meals on in-office days in the US and more.