Jiao Wang
Staff ML Engineer at Intel Corporation
California, United States
Summary
🤩
Rockstar🎓
Top SchoolJiao Wang is a Staff ML Engineer with 11+ years building distributed AI and big data systems, currently driving BigDL/Analytics Zoo and end-to-end AI pipelines at Intel from California. She has deep production experience integrating distributed deep learning with Spark, Ray, and Azure, and has led feature engineering, recommendation, and privacy-preserving ML solutions for enterprise customers like Mastercard and Burger King. An experienced speaker at Spark Summit, Strata and O’Reilly AI, she blends systems-level optimization with applied ML—recently contributing performance improvements for local LLM inference on Intel XPU (ipex-llm), including KV-cache optimizations for MPT/Aquila models. Her background spans early-career roles at Sun, SAP and GE Healthcare, pairing strong software engineering foundations with hands-on ML ops and platform design. Collectedly, she’s adept at taking research-grade models to scalable, production-ready big data deployments.
11 years of coding experience
9 years of employment as a software developer
Mater of Computer Science, Mater of Computer Science at University of San FranciscoBachelor, Computer Science, Bachelor, Computer Science at University of Electronic Science and Technology of China
Github Skills (6)
transformers10
pytorch10
gpu10
llm10
model-optimization9
optimization9
Programming languages (5)
Github contributions (5)
intel/ipex-llm
Feb 2017 - Jan 2023
Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, DeepSeek, Mixtral, Gemma, Phi, MiniCPM, Qwen-VL, MiniCPM-V, etc.) on Intel XPU (e.g., local PC with iGPU and NPU, discrete GPU such as Arc, Flex and Max); seamlessly integrate with llama.cpp, Ollama, HuggingFace, LangChain, LlamaIndex, vLLM, DeepSpeed, Axolotl, etc.
Role in this project:
ML Engineer
ML EngineerContributions:80 reviews, 663 commits, 225 PRs in 5 years 11 months
Contributions summary:Jiao contributed to optimizing the `ipex-llm` repository for large language model (LLM) inference and finetuning on Intel XPU, focusing on improving performance. Their work included implementing and optimizing KV cache mechanisms for models like MPT and Aquila, improving the overall efficiency. The user also made changes to support new models and integrated with various LLM frameworks.
llm-inferencellama2pythonfinetuningllama
jenniew/BigDL
Jan 2017 - Dec 2022
Contributions:448 commits, 1 PR, 496 pushes in 6 years
bigdldeep-learningspark-mlmachine-learningapache
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.