Machine Learning Engineer, GeForce G-Assist
Core
Building and optimizing an on-device AI assistant (GeForce G-Assist) combining Small Language Models, retrieval systems, and hybrid cloud capabilities for the GeForce ecosystem.
Role type
Senior Machine Learning Engineer (On-device AI & Systems)
Builds
GeForce G-Assist on-device AI assistant
Domain
Consumer Hardware / AI / Edge Computing
Deliverable
production ML models
Required skills
C/C++ (systems-level), Python, Small Language Models (SLMs), Retrieval-Augmented Generation (RAG), llama.cpp, Quantization, Memory optimization, Agentic AI workflows, Multimodal interactions
Preferred skills
Experience with user-facing language/multimodal models, Collaboration with product/platform teams, Translating user feedback into model improvements
Technologies
llama.cpp, C/C++, Python, SLMs, VLMs, RAG
Responsibilities
Evaluate and improve SLMs for accuracy and robustness in production; Optimize local inference (quantization, memory, performance); Design and integrate RAG systems; Support agentic AI workflows (planning, tool use)
Seniority
Senior, hands-on IC