LangChain
Infrastructure Engineer, Database
About this role
LangChain is seeking an Infrastructure Engineer to own the deployment, scaling, and operational reliability of SmithDB, a purpose-built database for AI observability. You'll manage Kubernetes infrastructure, infrastructure-as-code, CI/CD pipelines, and reliability engineering for a high-scale distributed system handling trillions of agent traces across multiple cloud environments.
What you'll do
- Own deployment and operations of SmithDB across cloud environments including cluster lifecycle, upgrades, and automated failover
- Build and maintain infrastructure tooling (Terraform, Kubernetes, Helm) for provisioning, configuring, and scaling database nodes
- Manage Kubernetes infrastructure for distributed database services handling multi-tenant, high-throughput, low-latency workloads
- Build deployment pipelines, rollout strategies, and infrastructure-as-code for the storage layer with safe promotion through environments
- Drive reliability engineering: incident response, postmortems, SLOs, disaster recovery, and capacity planning for massive-scale operations
- Collaborate with database internals engineers to translate engine features into production-ready infrastructure changes
What they're looking for
- Kubernetes and cloud infrastructure (AWS/GCP/Azure)
- Infrastructure-as-code (Terraform, Pulumi, or CDK)
- Systems programming/scripting (Go, Python, or similar)
- CI/CD tooling and deployment automation (Helm, ArgoCD)
- Stateful workload management and persistent storage
- On-call operations and incident response
- Capacity planning and cost optimization
- Container orchestration and distributed systems
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
LangChain
LangChain builds platforms and frameworks for developing, deploying, and observing production AI agents at enterprise scale, including LangSmith for AI observability and evaluation. The company is hiring Deployed Engineers to work directly with enterprise customers on agent implementation and operations, as well as Fullstack Engineers to build features across its platform stack.
- Website
- langchain.com
Likely interview questions
- Describe your experience deploying and managing stateful workloads in Kubernetes at scale—what were the biggest operational challenges you faced?
- Walk us through how you'd design a blue/green or rolling upgrade strategy for a distributed database serving high-traffic production customers.