About this role
Member of technical staff (Inference) - Paris at H. Location: Paris or London. Role: Develop pipelines, Optimize performance, Develop kernels Requirements: Develop scalable, low-latency inference pipelines; optimize model performance; develop GPU kernels; collaborate with research teams; strong CS/ML background; proficient in Python/C/C++; GPU programming experience. Category: Research and Development (R&D) Seniority: Mid Level Tools: Python, Rust, C/C++, CUDA, OpenAI Triton, Metal, Pytorch, ONNX Runtime Commitment: Full Time Workplace: Hybrid Languages: English