Senior Software Engineer
Core
Design, deploy, and maintain open-weight LLM serving infrastructure, sandbox runtimes, and vector/graph stores on Kubernetes.
Role type
Senior IC Infrastructure Engineer (LLM Serving & Systems)
Builds
Production-grade inference endpoints, sandbox environments, and data stores for backend services.
Domain
Cloud Infrastructure, Distributed Systems, LLM Serving
Deliverable
production ML models
Required skills
Rust, Go, C, C++, Zig, Kubernetes, Terraform, OpenTofu, Bicep, FastAPI, vLLM, SGLang, GPU scheduling, threat modeling, distributed systems optimization
Preferred skills
Tokio, controller-runtime, Kubebuilder, CRDs, KEDA, Karpenter, GPU device plugins, DRA, Firecracker, Kata, gVisor, secrets management, egress control, AWS, Azure, GCP
Responsibilities
Manage open-weight model serving deployment, configuration, SLOs, upgrades, and canaries; Administer Kubernetes inference workloads including operators, autoscaling, and GPU scheduling; Deploy and recover vector and graph stores; Own sandbox runtime lifecycle and control plane; Direct FastAPI control-plane services and debug dependent services; Maintain open-source engineering standards via pull requests and documentation.
Seniority
Senior, hands-on IC
