Yibo Peng
New York, New York, United States
Summary
🤩
Rockstar🎓
Top SchoolYibo Peng is a robotics and controls engineer with 4 years of hands-on experience combining industrial CAD/FEA tools (SolidWorks, Abaqus, Hypermesh, AutoCAD) with robotics simulation and RL toolchains (isaacgym, PyBullet) and production-grade programming in Python, C/C++, and Assembly. He has contributed to open-source ML infrastructure at Intel (ipex-llm), improving CI/CD and automating evaluation reports for local LLM inference—evidence of his ability to bridge research, tooling, and reproducible experiments. At Carnegie Mellon he co-developed EigenBot’s mechanical design and reinforcement-learning controllers, integrating CPG and trajectory generators to enhance hexapod locomotion. His Columbia work on 3D-woven carbon fiber lattices demonstrates an unusual mix of materials experimentation, FEA validation, and hands-on manufacturing. Based in New York with a Columbia MS in Robotics and Control and a Wuhan University background in energy and power engineering, he combines strong communication and self-regulation with a practical bias for shipping simulation-to-hardware solutions.
3 years of coding experience
Master of Science - MS, Robotics and control, Master of Science - MS, Robotics and control at 美国哥伦比亚大学学士, 能源与动力工程, 学士, 能源与动力工程 at 武汉理工大学
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (14)
transformers10
pytorch10
automation10
github-ci10
automations10
githubaction-workflow10
gpu10
python10
cicd10
llm10
pandas8
html7
bash7
csv7
Programming languages (4)
Github contributions (5)
intel/ipex-llm
Jan 2024 - May 2024
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:
DevOps Engineer
DevOps EngineerContributions:13 reviews, 25 PRs, 3 pushes in 4 months
Contributions summary:Yibo primarily contributed to the harness-evaluation workflow, modifying and adding features for statistical tables and result summarization. They made changes to the build and deployment steps, modifying paths, labels, and the overall structure of the evaluation process. The user integrated the generation of CSV and HTML reports, indicating a focus on automating the analysis of model performance. They also updated the CI/CD workflow for the nightly builds.
llm-inferencellama2pythonfinetuningllama
pengyb2001/BigDL
Jan 2024 - May 2024
Accelerate LLM with low-bit (FP4 / INT4 / FP8 / INT8) optimizations using bigdl-llm
Contributions:121 pushes, 41 branches in 3 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.