Tech Lead for WEKA's AI Inference team: leads and mentors a squad of ~3 engineers while staying hands-on building production LLM-serving infrastructure (vLLM, LMCache, NVMe token storage, RDMA data paths) optimized for high-throughput, low-latency inference. Core stack: Python, C++, CUDA, Kubernetes, GPU memory tiers.
Sign in to see your match
Connect over MCP — free, no account needed to search.