Charles Lovering
Research Scientist at Kensho Technologies
Greater Boston United States
Summary
👤
Senior🎓
Top SchoolCharles Lovering is a research scientist based in Greater Boston with a decade of experience at the intersection of machine learning research and software engineering. He holds a PhD in Computer Science from Brown University and currently applies his research expertise at Kensho Technologies after internships at Google and Microsoft. Charles has contributed to influential open-source ML tooling—integrating PromptSource tasks into EleutherAI’s lm-evaluation-harness—to expand few-shot evaluation and generation support. His background blends rigorous academic work with hands-on systems and full-stack development, enabling reproducible evaluation pipelines and tooling improvements. Colleagues describe him as someone who moves fluidly between prototyping novel research ideas and production-grade implementations. He brings a pragmatic curiosity, exemplified by adapting complex benchmarks to real-world evaluation frameworks.
11 years of coding experience
1 year of employment as a software developer
Doctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at Brown UniversityBachelor of Science (BS) / Master of Science (MS), Computer Science, Bachelor of Science (BS) / Master of Science (MS), Computer Science at Worcester Polytechnic Institute
English, German
Github Skills (5)
evaluation-framework10
python10
natural-language-processing9
nlp9
git7
Programming languages (4)
Github contributions (5)
EleutherAI/lm-evaluation-harness
Apr 2022 - Apr 2022
A framework for few-shot evaluation of language models.
Role in this project:
Full-stack Developer
Full-stack DeveloperContributions:43 commits in 3 days
Contributions summary:Charles's contributions primarily involve integrating PromptSource tasks into the lm-evaluation-harness framework. They added and adapted several tasks, including CoQA, DROP, and various SuperGLUE tasks, for compatibility with PromptSource. Furthermore, they modified the codebase to correctly handle generation tasks and enable saving examples. These changes indicate a focus on expanding the framework's capabilities and improving its integration with existing tools.
language-modelevaluation-frameworktransformer
cjlovering/playground
Jul 2016 - Dec 2020
Contributions:46 pushes, 2 branches in 4 years 5 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.