Machine Learning Engineer, GeForce G-Assist

What you’d do

Evaluate and improve small language models for GeForce G-Assist, focusing on accuracy, robustness, and conversational reliability, and mitigate issues like state drift and prompt leakage. Also optimize local inference with llama.cpp and write performance-critical C/C++ code. Found on the employer's careers page on Oct 17, 2026. Apply through the link.

You’ll need

• SLM and VLM architecture experience
• llama.cpp optimization
• Quantization and memory tuning
• C/C++ coding in performance-critical paths