Cheen Tan
AI Software Development Engineer at Intel Corporation
Penang, Malaysia
Summary
🤩
Rockstar🎓
Top SchoolCheen Tan is an AI software development engineer with a PhD in Electrical & Electronics Engineering and four years of industry experience building generative AI and computer vision systems. At Intel he led backend teams for production-grade chatbots and RAG pipelines, contributed to the IPEX-LLM acceleration library by hardening GPU test suites, and showcased solutions at MWC, CES and Computex. His background blends academic research—publishing and patenting work on rain removal, traffic and in-cabin monitoring—with hands-on MLOps and deployment experience using LangChain, LlamaIndex, MLflow and DVC. He is comfortable across the stack from C++ real-time vision pipelines to Python LLM integrations and benchmarking on Intel hardware. Known for turning research prototypes into deployable products, he also drives team capability-building through workshops and technical hiring. Based in Penang, Malaysia, Cheen combines rigorous experimentation with pragmatic engineering to accelerate AI features from prototype to production.
4 years of coding experience
2 years of employment as a software developer
Doctor of Philosophy - PhD, Electrical and Electronics Engineering, Doctor of Philosophy - PhD, Electrical and Electronics Engineering at Nanyang Technological University
Github Skills (8)
transformers10
test-framework10
pytest10
gpu10
python10
testing10
cicd9
bash8
Programming languages (3)
Github contributions (5)
intel/ipex-llm
Oct 2023 - Mar 2024
Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, 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, GraphRAG, DeepSpeed, Axolotl, etc
Role in this project:
QA Engineer / Test Automation Engineer
QA Engineer / Test Automation EngineerContributions:19 reviews, 19 PRs, 1 push in 5 months
Contributions summary:Cheen primarily contributed to the testing infrastructure and test suite of the repository. They added unit tests for optimized model correctness, enabling and configuring a GPU-based testing workflow. The user also introduced regression tests, including those for optimizing models on the GPU. Furthermore, they modified test scripts and configurations to ensure consistent and effective testing across different environments.
llm-inferencellama2pythonfinetuningllama
chtanch/ipex-llm
Oct 2023 - May 2024
Accelerate LLM with low-bit (INT3 / INT4 / NF4 / INT5 / INT8) optimizations using bigdl-llm
Contributions:150 pushes, 40 branches in 7 months
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.