Member of Technical Staff, Forward Deployed Engineer
Core
Deploy, integrate, debug, and optimize vLLM-powered inference systems across cloud, Kubernetes, GPU, and networking environments for real customers. (via careerplan.io/jobs/b127864f-5c71-4c96-90ce-cb20c57391a9-member-of-technical-staff-forward-deployed-engineer-at-inferact)
Role type
Senior IC forward-deployed engineer (ML inference systems)
Builds
Production-grade vLLM inference deployments and reusable product capabilities
Domain
AI/ML inference, cloud infrastructure, GPU computing
Deliverable
production ML models
Required skills
Python, Go, TypeScript, Kubernetes, ML system deployment, systems debugging, latency/throughput optimization, distributed systems
Preferred skills
vLLM, SGLang, TensorRT-LLM, NVIDIA/AMD GPUs, CUDA/ROCm, enterprise infrastructure deployment, API/SDK/CLI development, performance profiling
Technologies
vLLM, Kubernetes, Python, Go, TypeScript, NVIDIA GPUs, CUDA, ROCm, Ray Serve, BentoML
Responsibilities
Work directly with customers to deploy and integrate inference systems, debug production issues end-to-end, optimize performance and cost tradeoffs, and translate field learnings into product features
Seniority
Senior, hands-on IC
