jobs
Machine Learning Engineer, GeForce G-Assist
At NVIDIA, we’re building GeForce G-Assist — an on-device AI assistant that combines Small Language Models (SLMs), retrieval systems, and hybrid cloud capabilities to deliver responsive…
Em inglês
- Company
- NVIDIA
- Location
- US, CA, Santa Clara
- Status
- Open
- Posted
- 2026-11-19
NVIDIA is hiring an engineer for GeForce G-Assist, an on-device assistant combining small language models with retrieval and cloud models. The role centers on evaluating SLMs for accuracy and conversational reliability, curbing state drift and retrieval cross-talk, tuning local inference with llama.cpp and quantization, writing C/C++ in performance-critical code, and building RAG and agentic tool-use flows. The posting asks for five or more years in system software, a master's degree or equivalent, strong C/C++ and Python, and hands-on SLM evaluation. It stresses production behavior over benchmark scores.
Original job posting