Douglas Hanley
Software Engineer at University of Pittsburgh
Madison, Wisconsin, United States
Summary
🤩
Rockstar🎓
Top SchoolDouglas Hanley is a software engineer and academic with 24 years of experience who blends machine learning engineering with rigorous economic research. Based in Madison, WI, he contributes to efficient LLM inference (notably extending the popular llama.cpp project to support BERT embeddings, WordPiece tokenization, and GGUF conversion) while building generative-AI tooling for rapid visual design at Compendium Labs. He also serves on the faculty at the University of Pittsburgh, bringing an economist’s empirical instincts to model evaluation and product experimentation. Comfortable across backend inference stacks and front-end rapid-iteration interfaces, he focuses on making open-weight models practical for real-time creative workflows. His background—PhD in Economics from Penn and a BS from Caltech—pairs deep quantitative training with hands-on systems engineering, a combination that surfaces both novel research insights and production-ready implementations.
24 years of coding experience
9 years of employment as a software developer
California Institute of TechnologyDoctor of Philosophy (PhD), Economics, Doctor of Philosophy (PhD), Economics at University of Pennsylvania
Github Skills (12)
llama10
tokenize10
machine-learning10
tokenizer10
nlp10
c-language10
gm10
cprogramming-language10
bert10
gfs9
gf9
gff9
Programming languages (9)
Github contributions (5)
ggml-org/llama.cpp
Mar 2023 - Oct 2024
LLM inference in C/C++
Role in this project:
ML Engineer
ML EngineerContributions:47 reviews, 13 PRs, 1 push in 1 year 7 months
Contributions summary:Douglas primarily contributed to adding support for BERT embedding models within the `llama.cpp` project. This included implementing BERT model graph construction, developing a WordPiece tokenizer, and enabling the conversion of BERT models to GGUF. Their work involved adding new LLM architectures and tensor definitions to accommodate BERT-based models, demonstrating a focus on expanding the project's capabilities to support a wider range of language models. Further contributions included implementing improvements to tokenization and pooling, and allowing embeddings on any model.
ggmlllama
iamlemec/fastpat
Feb 2012 - Aug 2022
Contributions:155 commits, 2 PRs, 123 pushes in 10 years 7 months
patent-datausptopatentparseanalyze
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.