Platform Engineer III
Core
Build and optimize AI Platform capabilities on GCP/GKE to enable product teams to deploy Generative AI applications and self-hosted models.
Role type
Senior Platform Engineer (AI Infrastructure)
Builds
Cloud-native AI tools, observability standards, and reusable platform templates for Generative AI workloads.
Domain
Cloud-native AI infrastructure, Generative AI, Kubernetes
Deliverable
production ML models
Required skills
Self-hosted LLM serving, Kubernetes GPU management, OpenTelemetry instrumentation, GenAI frameworks, Cloud-native networking, Python/Go programming, Infrastructure as Code
Preferred skills
Agentgateway/Kagent integration, Istio Ambient Mode, NVIDIA NIM/vLLM/SGLang experience
Technologies
GKE, GCP, vLLM, NVIDIA NIM, SGLang, Agentgateway, Kagent, OpenTelemetry, LangGraph, LangChain, Google ADK, Vertex AI, Gemini APIs, Istio, ArgoCD, Flux, Terraform
Responsibilities
Implement and optimize AI Platform capabilities on GKE/GCP; Apply software engineering best practices (CI/CD, GitOps, OTel) to maintain platform components; Collaborate with teams to troubleshoot integration issues and implement cloud-native AI tools; Build custom K8s resources and telemetry pipelines; Contribute to technical documentation and reusable platform templates; Execute roadmaps to improve platform reliability and delivery speed.
Seniority
Senior, hands-on IC