About this role
Senior Inference Engineer at DRIVENETS. Location: Tel Aviv, Tel Aviv District, Israel. Role: designing infrastructure, building infrastructure, provisioning clusters Requirements: 5+ years backend engineering (2+ years in ML inference), deep knowledge of transformer attention and KV cache design, hands-on with inference engines, strong Python and C++/CUDA familiarity, GPU cluster and Kubernetes experience. Category: Software Development Seniority: Senior Level Tools: vLLM, TGI, TensorRT-LLM, TRT-LLM, Triton, Triton Inference Server, SGLang, Python, C++, CUDA, A100, H100, H200, Kubernetes, SSE, gRPC, WebSocket, GPTQ, AWQ, FP8, INT8, NVIDIA NIM Commitment: Full Time Workplace: Hybrid Languages: English