Chengpeng Hu
Senior Staff Partner Engineer, GenAI at Meta
Menlo Park, California, United States
Summary
🤩
Rockstar🎓
Top SchoolChester Hu is a software engineer with 11 years of experience, currently based in Menlo Park and working as a Partner Engineer, AI at Meta. He blends machine learning engineering and frontend development, demonstrated by his implementation of a RAG chatbot using Llama 2—building the Gradio UI, integrating a text-generation-inference server, and wiring LangChain for retrieval. Chester focuses on practical, demo-driven solutions that make advanced models accessible to partners and developers. He brings production-minded instincts from both API and UI layers, enabling end-to-end ML experiences rather than isolated prototypes. Colleagues can expect a pragmatic engineer who translates cutting-edge research into interactive, usable tools for real-world workflows.
11 years of coding experience
9 years of employment as a software developer
Master's Degree Computer Software Engineering, Master's Degree Computer Software Engineering at University of Illinois Urbana-ChampaignWuhan Foreign Languages School
Chinese, Japanese, English
Stackoverflow
51reputation
9kreached
0answers
5questions
Github Skills (21)
pytorch10
python10
langchain10
llama10
llm10
gradio10
ai10
fine-tuning9
api9
eclipse6
viewcontroller6
point-cloud6
uinavigationcontroller6
android6
point-cloud-library6
Programming languages (6)
Github contributions (5)
meta-llama/llama-cookbook
Sep 2023 - Apr 2025
Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services
Role in this project:
ML Engineer & Frontend Developer
ML Engineer & Frontend DeveloperContributions:56 reviews, 17 PRs, 34 pushes in 1 year 7 months
Contributions summary:Chengpeng implemented a Retrieval Augmented Generation (RAG) chatbot example using Llama 2. They built the chatbot UI with Gradio, integrated it with a text-generation-inference API server, and integrated RAG capabilities using Langchain. The primary focus was on creating a functional and interactive demo showcasing how to build a chatbot capable of answering questions based on a user's own data, using the Llama 2 model.
aifinetuninglangchainllamallama2
WuhanMonkey/Test-Impedance
Feb 2015 - Aug 2016
Contributions:12 pushes, 1 branch in 1 year 6 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.