Summary
Yury Nahshan is an LLM Application Engineer with seven years of deep learning and systems experience, currently advancing generative AI at NVIDIA. He has a strong track record in efficient training and inference—shaping LLM scalability and optimization across roles at Toga Networks (Huawei), Habana Labs, and Intel. Yury blends research-driven methods (quantization, pruning, sparsity) with production engineering, building PyTorch tools and platform integrations that moved academic ideas into deployable systems. Based in Haifa, he pairs a Technion CS background and a master's in progress with hands-on low-level experience from silicon debugging to hardware-aware model acceleration. Notably, his career emphasizes practical performance wins: squeezing model efficiency at every layer from numerical formats to inference pipelines.
7 years of coding experience
17 years of employment as a software developer
Bachelor's Degree Computer Science, Bachelor's Degree Computer Science at Technion - Israel Institute of Technology
Practical Engineer Electronics, Practical Engineer Electronics at Basmat technical colledge
Master's degree Computer Science, Master's degree Computer Science at The Open University of Israel
Russian, English, Hebrew