N
Senior System Software Engineer - Local AI
Nvidia 1
India, Pune
≈ 174,2 тыс.–334,4 тыс. ₽ · 2,2 тыс.–4,2 тыс. $ · 1,9 тыс.–3,6 тыс. €
208 333 – 400 000 INR
🏢 Офис
Senior
Полная занятость
Продуктовая
Tech
Описание вакансии
Обязанности
•Build local AI inference software
•Debug and optimize system-level performance
•Design inference execution stacks
•Develop infrastructure for performance and accuracy sweeps
•Establish engineering guidelines for model bring up and production readiness
•Implement model optimization quantization pruning sparsity distillation
•Optimize inference runtimes for performance stability scalability
Технологии: C++, CUDA, Deep learning, DirectX, Generative AI, Graph Execution, KV cache, Knowledge Distillation, Llama.cpp, Machine Learning, Memory Management, Pruning, PyTorch, Quantization, Scheduling, Sparsity, TensorRT, VLLM, Vulkan, WinML