About this role
Tech Lead Manager, Inference at Luma. Location: Redwood City, California, United States. Role: architecting platform, leading team, debugging incidents Requirements: 8+ years building large-scale distributed systems or ML infrastructure with experience operating model-serving/inference platforms, strong Python and PyTorch, Kubernetes experience, technical leadership, and hands-on platform engineering. Category: Engineering Seniority: Senior Level Tools: vLLM, SGLang, TensorRT-LLM, Python, PyTorch, Kubernetes, FFmpeg, RDMA, InfiniBand, NVLink, Ray, Rust, C++, CUDA, HIP Commitment: Full Time Workplace: Hybrid Languages: English