AI Platform Engineer
Core
Design, build, and operate a Kubernetes-based AI platform runtime, gateways, routing, model caching, and shared RAG services while providing AI FinOps capabilities.
Role type
Senior IC AI Platform Engineer
Builds
Kubernetes-based AI platform runtime, gateways, routing, model caching, shared RAG services, and prompt/skills management
Domain
Cloud-native infrastructure, MLOps/LLMOps, regulated industries
Deliverable
production ML models
Required skills
Kubernetes, Python, TypeScript, Go, Terraform, MLOps/LLMOps, vector databases, routing and caching, identity and risk management, AI FinOps, infrastructure-as-code
Preferred skills
Vendor evaluation, cross-functional partnership, pragmatic product sense, decision-making under ambiguity
Technologies
Kubernetes, Python, TypeScript, Go, Terraform, vector databases
Responsibilities
Design and operate platform runtime, gateways, routing, and caching layers; implement AI FinOps capabilities including quotas and cost controls; define and maintain platform standards, SDKs, and MCP interfaces; implement metrics, logs, traces, and incident response processes; optimize scalability, reliability, and cost across regions; partner with governance owners and hyperscalers on regulated-industry features
Seniority
Senior, hands-on IC