Darrell S. Best Jr.

Washington, D.C., United States

> DOD TS/SCI Cleared

Read My Articles Contact Me

Professional Summary

  • AI Research Engineer with over a decade of programming experience and 6+ years delivering complex AI/ML solutions.
  • Led AI projects including multilingual LLMs, federated learning systems, FPGA bitstream error correction, and medical text classification.
  • Proven track record in using PyTorch, Hugging Face, DeepSpeed, and Flower to deliver scalable, secure, and efficient AI systems.
  • Developed mission-critical AI solutions for defense, healthcare, and telecommunications, driving operational efficiency and innovation.

Work Experience

Senior Research Engineer II, Information Sciences Institute — Arlington, VA

Jul 2019 – Present
  • HealthMap : Mapping unstructured medical reports to ICD codes and predicting conditions with AI.
  • GreenSight : Engineered text encoders with Hugging Face to classify text by Schwartz’s 19 moral values.
  • Sonic Screwdriver : Created FPGA bitstream error correction with custom tokenization, MLM training, and Hugging Face tools.
  • Danube : Built federated learning models with Flower for secure and anomaly-resistant distributed AI training.
  • Hawkeye : Developed multilingual LLMs using GPT-2 and DeepSpeed for scalable foreign language chat systems.

Machine Learning Engineer, QinetiQ US — Lorton, VA

Mar 2018 – Jul 2022
  • HMDS : Built IED detection systems using ground-penetrating radar for Army Husky vehicles and integrated software into Army training simulators.
  • IGSR : Developed border-crossing detection for the FBI using ResNet CNNs for high-accuracy image recognition.
  • Served full-time from March 2018 to July 2019, then part-time consulting from July 2019 to August 2022.

Junior Software Engineer, Windstream — Greenville, SC

Sep 2017 – Mar 2018
  • PUMA: Built end-to-end provisioning software for DSLAMs and network devices using multiple databases and remote connections.

Research Assistant, Clemson University — Clemson, SC

May 2014 – Feb 2018
  • Eye-Tracking Research: Solved the Midas touch problem with natural eye gestures, enabling faster, intuitive user control.
  • Published: A Rotary Dial for Gaze-based PIN Entry (ETRA 2016)

Education

MS in Computer Science

2024 – Present
  • University of Southern California, Viterbi School of Engineering
  • Focus: Data Science

Graduate Coursework

  • CSCI 561 — Foundations of Artificial Intelligence: Search algorithms, constraint satisfaction, probabilistic reasoning, and game-playing agents.
  • CSCI 570 — Analysis of Algorithms: Advanced algorithm design and complexity analysis including dynamic programming, graph algorithms, and NP-completeness.
  • CSCI 544 — Applied Natural Language Processing: Neural language models, sequence-to-sequence architectures, transformers, and text classification pipelines.
  • CSCI 585 — Database Management Systems: Relational and NoSQL databases, query optimization, transaction processing, and distributed data systems.
  • CSCI 567 — Machine Learning: Supervised and unsupervised learning, kernel methods, ensemble techniques, and deep learning fundamentals.

Publications

A Rotary Dial for Gaze-based PIN Entry

Best, Darrell S. and Duchowski, Andrew T. (2016). In Proceedings of the Ninth Biennial ACM Symposium on Eye Tracking Research & Applications (ETRA '16), pages 69–76. ACM.

https://doi.org/10.1145/2857491.2857527

View on Google Scholar

Skills

Languages

Python JavaScript C++ SQL Bash

AI / ML

PyTorch Hugging Face TensorFlow DeepSpeed Flower scikit-learn

DevOps & Tools

Docker Git CI/CD Linux

Contact

Open to collaborations in AI research and engineering. Feel free to reach out.

Email:

LinkedIn: linkedin.com/in/darrellsbest

Scholar: Google Scholar

GitHub: github.com/DarrellBest