Intel · 2021–2023
Selected engineering work and technical writing from my time as an AI Frameworks Engineer at Intel, focused on Neural Coder, model optimization, developer tooling, and performance benchmarking for deployed machine learning systems.
Core project · Neural Coder
At Intel, I led the development of Neural Coder, a component of Intel Neural Compressor that automated the insertion and evaluation of deep learning optimizations in existing Python code. It combined static program analysis—syntax analysis, type inference, and call graph parsing—with automated benchmarking and brought the workflow from PyTorch scripts to Hugging Face Transformers, Alibaba Cloud PAI-DSW, JupyterLab, and Visual Studio Code.
Neural Coder was demonstrated in Intel CEO Pat Gelsinger’s Intel Innovation 2022 keynote. This work was recognized internally at Intel with the AIA Division Achievement Award for Neural Coder innovation (2022) and the CESG SW AI Division Recognition Award for the Alibaba Cloud collaboration (2023); both are listed on my professional profile.
Technical writing from Intel
Showed how Neural Coder automatically enabled Optimum Intel INT8 quantization for Hugging Face Transformers. The evaluated workflow covered 18 PyTorch tasks using the Transformers Trainer and reported about 1.7× inference acceleration on 3rd Gen Intel Xeon processors, typically with less than 1% accuracy loss.
Presented a Visual Studio Code extension that applied static or dynamic INT8 quantization and BF16 optimization, preserved generated code changes as inspectable patches, and benchmarked candidate transformations directly inside the editor.
Documented an Intel–Alibaba integration that brought Neural Coder into Alibaba Cloud PAI-DSW and exposed BladeDISC as an optimization backend, enabling streamlined optimization and automatic comparative benchmarking from JupyterLab.
Introduced Neural Coder, a streamlined workflow combining deep learning optimization rules with Python syntax analysis, static type inference, and call graph parsing to insert quantization code into PyTorch scripts and benchmark applicable optimizations.