N
Senior System Software Engineer - LocalAI
Nvidia 1
India, Pune
≈ 174,2 тыс.–348,3 тыс. ₽ · 2,2 тыс.–4,4 тыс. $ · 1,9 тыс.–3,8 тыс. €
208 333 – 416 667 INR
🏢 Офис
Senior
Полная занятость
Продуктовая
Tech
Описание вакансии
Обязанности
•Align technical requirements and priorities with cross functional teams
•Analyze results to identify gaps and drive fixes
•Build and optimize local AI inference stack
•Debug and tune system performance and accuracy trade offs
•Design and develop inference runtimes and execution stacks
•Develop infrastructure for performance and accuracy sweeps
•Establish engineering guidelines for bring up and production readiness
•Implement model optimization including quantization pruning sparsity distillation
•Optimize AI models data pipelines and inference runtimes
Технологии: C++, CUDA, DXCGC, DirectX, Llama.cpp, PyTorch, TensorRT, TensorRT-RTX, VLLM, Vulkan, WinML