Senior Software Engineer (AI Inference & Runtime Platform)

Job Description

Own the AI inference control plane and agent-sandboxing platform, managing GPU clouds and Kubernetes clusters. Responsible for the deployment of open-weight models, secure microVM isolation, and the stateful data plane including vector and graph stores.

Requirements: Requires 5+ years of experience in systems languages like Rust or Go and a strong background in operating Kubernetes at scale. Must have expertise in threat modeling isolation boundaries and deploying LLM serving infrastructure such as vLLM or SGLang.

Key Skills: Rust, Kubernetes, Python, FastAPI, GPU Scheduling, LLM Serving, Threat Modeling, Distributed Systems, Infrastructure as Code, Container Isolation, Vector Databases, Graph Databases, Go, C++, Terraform, OpenTelemetry

Benefits: Competitive early-stage startup compensation, Bonus eligibility, Health insurance, Flexible paid time off, Equity