About this role
Machine Learning Engineer, Inference at Rime. Location: United States. Role: build inference, optimize latency, deploy broadly Requirements: Strong software engineering, production ML inference, low latency systems, experience with inference engines and speech tech. Category: Software Development Seniority: Mid Level Tools: Rust, Python, C++, CUDA, TensorRT, ONNX, Triton, vLLM, SGLang, CUDA Graphs Commitment: Full Time Workplace: Remote Languages: English