Farris Atif

About Me

I am a Machine Learning Engineer at Mercedes-Benz R&D North America, specializing in the e2e development and integration of LLMs and CV solutions across embedded automotive platforms

Research Interests

• Accelerated LLM Inference: tinkering w/ runtimes for non-traditional embedded targets
  (e.g., llama.cpp, onnx-genai, qnn, mlx) to optimize token throughput & generation ⚡
• Model Optimization: pruning, quantization, distillation, and advanced KV-caching strategies to improve inference efficiency and user experience

Publications

++

• In my free time I enjoy traveling, working out/hiking, and watching the 49ers 🏈