Machine Learning Engineer, GeForce G-Assist
$152k - $288k • Remote • US, CA, Santa Clara
Posted 3d ago
About the job
NVIDIA is building GeForce G-Assist, an on-device AI assistant that integrates Small Language Models (SLMs), retrieval systems, and hybrid cloud capabilities for responsive, context-aware assistance within the GeForce ecosystem. This role involves close collaboration across engineering and product teams to ensure G-Assist performs reliably in real-world scenarios. The focus is on production model behavior rather than just benchmarks, with an emphasis on accuracy, robustness, and conversational reliability. The team works with SLM and VLM architectures, hybrid cloud/local model architectures, and optimizes local inference for performance.
Responsibilities
- Evaluate and improve Small Language Models for accuracy, robustness, and conversational reliability.
- Identify and mitigate conversation and context contamination issues like state drift, prompt leakage, and retrieval cross-talk.
- Work with SLM and VLM architectures for text and multimodal interactions.
- Collaborate on hybrid architectures combining local SLMs with cloud-based models.
- Optimize local inference using llama.cpp, focusing on quantization, memory usage, and performance tuning.
- Read, write, and optimize C/C++ code in performance-critical paths.
- Design and integrate retrieval-augmented generation (RAG) systems.
- Support agentic AI workflows, including planning, tool use, and multi-step execution.
Requirements
- 5+ years of validated experience in system software or a related field, with an M.S. or higher degree in Computer Science, Data Science, Engineering, or equivalent experience.
- Strong ability to read and write C/C++ code in systems-level or performance-sensitive environments.
- Proficiency in Python.
- Hands-on experience with llama.cpp or similar local inference frameworks.
- Hands-on experience evaluating Small Language Models, including task-based and conversational testing.
- Understanding of conversation dynamics, long-context behavior, and contamination challenges.
- Knowledge of SLM and VLM architectures and their trade-offs.
- Experience with retrieval technologies and language-model integration.
- Familiarity with agentic AI patterns such as tool use and planning.
Benefits
- Equity
- Benefits package