About this role
LLM Inference Engineer at Near AI. Location: San Francisco or United States. Role: architecting systems, optimizing inference, maintaining systems Requirements: Expert in LLM inference and serving systems, optimizing throughput/latency/cost for open-source LLMs, deep GPU architecture knowledge, and experience with PyTorch, Triton, CUDA and inference engines like vLLM/SGLang/TensorRT. Category: Software Development Seniority: Senior Level Tools: SGLang, vLLM, TensorRT, PyTorch, Triton, CuTe, CUDA Commitment: Full Time Workplace: Remote Languages: English