Bojun Feng
Software Development Engineer at Amazon
Austin, Texas Metropolitan Area United States
Summary
🤩
Rockstar🎓
Top SchoolBojun Feng is a Software Development Engineer with four years of experience building reliable network and cloud systems, currently working on scalable infrastructure at Amazon in the Austin area. He combines a strong academic foundation from the University of Chicago (MS Computer Science) with hands-on ML and data-science work, from finetuning GPT-4o for decision‑making research to topological analysis of behavioral data. Bojun contributes to prominent open-source ML tooling—improving documentation in the widely-used Hugging Face transformers repo—and has engineered LLM inference support (chatglm family) and performance wins in Xinference. He has a track record of shipping full-stack systems on AWS, optimizing GPU inference throughput, and designing data pipelines that turn noisy signals into actionable model inputs. Practical, research‑savvy, and detail-oriented, he bridges production-grade network engineering with applied machine learning.
4 years of coding experience
4 years of employment as a software developer
Solving Global Challenges, Solving Global Challenges at Yale Young Global ScholarsHigh School Diploma, High School Diploma at Westtown SchoolMaster of Science - MS Computer Science, Master of Science - MS Computer Science at University of Chicago
Github Skills (13)
pytorch10
nlp10
inference10
python10
natural-language-processing10
documentation10
llm10
machine-learning9
gm9
gml9
language-model8
transformers8
pre-trained-model8
Programming languages (9)
Github contributions (5)
xorbitsai/inference
Jul 2023 - Oct 2025
Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-ready inference API.
Role in this project:
ML Engineer
ML EngineerContributions:7 reviews, 35 PRs, 3 pushes in 2 years 3 months
Contributions summary:Bojun primarily contributed to the integration and support of various LLMs, specifically focusing on the 'chatglm' family of models. Their work included adding support for 'chatglm-6b', adding both versions of 'chatglm', updating tests, and addressing issues related to model parameters within the 'xinference' project, aligning with the project's focus on providing LLM inference capabilities. The user also addressed a bug related to the model max_length configurations.
gptinferencellmmultimodalspeech
huggingface/transformers
Oct 2023 - May 2025
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Role in this project:Technical Writer
Technical WriterContributions:5 PRs, 13 comments in 1 year 7 months
Contributions summary:Bojun primarily focused on improving and updating documentation within the Hugging Face Transformers repository. Their commits involved fixing docstrings, updating configurations, and correcting typos in warning messages related to library usage. The user also worked on cleaning up code and improving the documentation of different tokenizer classes within the codebase. These contributions enhance the clarity and usability of the library for developers.
audioinferencemachine-learning-modelsmultimodaltransformers
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.