Derek Miller
Vice President Of Platform Research
Boston, Massachusetts, United States
Summary
🤩
Rockstar🎓
Top SchoolDerek Miller is a seasoned machine learning and platform leader with 11 years of experience, currently serving as Vice President of Platform Research at DeepCure in Boston. He progressed through technical and leadership roles at DeepCure—from ML Architect to Director of Machine Learning—building ML platforms that bridge research and production for drug discovery. Derek combines a strong academic foundation from Georgia Tech with hands-on software engineering experience dating back to senior engineering roles and research assistance at Ball State. He is an active open-source contributor, notably enhancing a BERT-based extractive summarizer with coreference resolution, model additions like DistilBert, and practical services for summarization by ratio and elbow analysis. Known for turning NLP and ML research into deployable services, he brings a pragmatic, product-focused approach to complex AI problems and platform scalability.
11 years of coding experience
12 years of employment as a software developer
Master of Science - MS Computer Science, Master of Science - MS Computer Science at Georgia Institute of TechnologyBachelor's degree Telecommunications, Bachelor's degree Telecommunications at Ball State University
Stackoverflow
1,038reputation
159kreached
25answers
7questions
Github Skills (16)
transformers10
pytorch10
machine-learning10
nlp10
spacy10
python10
bert10
scikit-learn9
scikit9
mediator6
spark-jobserver6
apache-spark6
reinforcement-learning6
scala6
dataframe6
Programming languages (8)
Github contributions (5)
dmmiller612/bert-extractive-summarizer
May 2019 - Jan 2022
Easy to use extractive text summarization with BERT
Role in this project:
ML Engineer
ML EngineerContributions:16 releases, 1 review, 140 commits in 2 years 8 months
Contributions summary:Derek contributed to the development of an extractive text summarization tool, modifying core files and adding new features. They implemented coreference resolution using neuralcoref and integrated SpaCy. The user also incorporated new models like DistilBert, added type hints, and updated dependencies for the project. The user also created a service to summarize text by ratio and sentences, and added the elbow analysis feature.
pytorchnlpdistilbertbertsentence-embeddings
lifeomic/spark-vcf
Nov 2017 - Jan 2019
Spark VCF data source implementation for Dataframes
Contributions:1 release, 34 commits, 14 PRs in 1 year 2 months
team-clinical-intelligenceemrgenotypelifeomicdata-source
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.