SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 180,000 - 230,000 / annual
LangChain is hiring a Database Infrastructure Engineer to own the deployment, operations, and reliability of SmithDB, an internal database system purpose-built for AI observability and evaluation. SmithDB is a greenfield, production-grade system handling trillions of agent traces with industry-leading performance and scalability.
In this role, you will own the complete infrastructure layer for SmithDB across cloud environments (AWS, GCP, Azure). Key responsibilities include:
- Cluster lifecycle management, blue/green and rolling upgrades, and automated failover across multi-cloud deployments
- Building and maintaining infrastructure-as-code (Terraform, Kubernetes, Helm) for provisioning, configuring, and scaling SmithDB nodes
- Kubernetes infrastructure for distributed, multi-tenant, high-throughput, low-latency database services
- Deployment pipelines, rollout strategies, and safe promotion workflows from dev through production
- Reliability engineering: incident response, postmortems, SLOs, disaster recovery, and capacity planning
- Cost optimization and resource rightsizing to handle traffic spikes from large customers without manual intervention
- CI/CD pipeline development for database infrastructure changes
- Close collaboration with SmithDB internals engineers to translate engine features into production-ready infrastructure
You'll need 5+ years in infrastructure, platform engineering, or SRE with strong hands-on Kubernetes and cloud experience. Deep familiarity with at least one major cloud provider, infrastructure-as-code fluency (Terraform as primary language), and operational instincts from on-call experience with high-traffic data systems are essential. Strong scripting ability (Go, Python, or similar), container orchestration expertise, and a bias toward automation are required. Nice-to-haves include production database ownership (Postgres, ClickHouse, Redis) and comfort reading Rust.
LangChain is a Series B company ($125M raised from IVP, Sequoia, Benchmark, CapitalG, Sapphire Ventures) with 100M+ monthly open-source downloads, 6,000+ active LangSmith customers, and adoption across Fortune 500 companies including Klarna, Coinbase, Workday, and Nvidia. The SmithDB team is small, fast, and tackling genuinely hard systems problems with real production load and ambitious engineering goals.
About LangChain
AI / Data / Infrastructure — developer platform and framework for building LLM applications and agents.
