Darron Fuller, Developer in Washington, DC, United States
Darron is available for hire
Hire Darron

Darron Fuller

Verified Expert  in Engineering

Machine Learning Engineer and Developer

Location
Washington, DC, United States
Toptal Member Since
July 29, 2019

Darron has 15 years of experience in R&D and client-facing roles as lead engineer of mission-critical artificial intelligence and machine learning and advanced analytics software for notable clients in global media, renewable energy industries, and the U.S. Department of Defense. Darron holds a BSc in computer science and an MSc in data analytics engineering with disciplines in AI and machine learning, decision optimization/mathematical modeling, and computational statistics.

Portfolio

StreamEdge Analytics, LLC
Amazon Web Services (AWS), Graphics Processing Unit (GPU), Jupyter, Pandas...
OctoAI, Inc.
Python, PyTorch, Machine Learning, Testing, Natural Language Processing (NLP)...
LiveView Technologies
Machine Learning, Artificial Intelligence (AI), Computer Vision...

Experience

Availability

Full-time

Preferred Environment

Amazon Web Services (AWS), Python, Agile, Pandas, PyTorch, Data Science, Convolutional Neural Networks (CNN), Docker, Containerization, Generative Pre-trained Transformers (GPT)

The most amazing...

...project I've developed was an advanced energy market trading algorithm with multiple machine learning (predictive) and optimization (prescriptive) models.

Work Experience

Lead Machine Learning Engineer

2013 - PRESENT
StreamEdge Analytics, LLC
  • Worked as a senior machine learning engineer on Comcast Labs' applied AI research and engineering team that owns the full stack and operationalization of voice and video analysis product offerings and advanced analytics and ML pipelines.
  • Architected, developed, and deployed the Comcast Machine Learning Infrastructure supporting inference for Xfinity Home Security cameras. TensorFlow/OpenVINO object-detection models on AWS EKS/Kubernetes, Prometheus, and Grafana for observability.
  • Designed and implemented observability and monitoring capability of the Comcast Xfinity Voice Assistant Platform that is used by millions of customers. Applied machine learning and cloud technologies to process billions of natural language queries.
  • Worked on R&D machine learning modeling for anomaly detection in Comcast Xfinity Home Security customers using a variety of home sensor events (e.g., motion, door, window, wifi connections, etc.).
  • Worked as a machine learning research and development engineer for Comcast Network Product and Services Division/Insights and Analytics Division, an R&D of machine learning anomaly detection models for detecting anomalous network events in Comcast network operations.
  • Developed predictive models to improve the effectiveness of child support collection activities and monitoring children's health and safety in foster care. I oversaw the project as the lead machine learning engineer.
  • Developed multi-terabyte automated vehicle location data sets for public transit systems. Applied data mining, statistical inference, and machine learning to identify unsafe operational practices in public transportation systems.
  • Supported the special activities for the Chairman of the Joint Chiefs of Staff, Office of Secretary of Defense, and Defense Manpower Data Center. Developed advanced analytics for mission-critical manpower analytics and logistics systems.
  • Collaborated as the teaching and technical assistant to the lead instructors for the Predictive Analytics for Healthcare workshop of the largest conference on predictive analytics.
Technologies: Amazon Web Services (AWS), Graphics Processing Unit (GPU), Jupyter, Pandas, Python, GitHub, Git, Google Cloud Platform (GCP), TensorFlow, Keras, Scikit-learn, Amazon S3 (AWS S3), Amazon SageMaker, Databricks, Predictive Modeling, API Integration, Data Science, PostgreSQL, Time Series Analysis, Natural Language Processing (NLP), Testing, Artificial Intelligence (AI), Object Recognition, Computer Vision Algorithms, OpenCV, Image Processing, Neural Networks, Time Series, Forecasting, Docker, FastAPI, Containerization, Generative Pre-trained Transformers (GPT), Data Modeling, Algorithms, Data Matching, CSV File Processing, Natural Language Toolkit (NLTK), Unit Testing, Pytest, pylint, API Management, APIs, Cloud Platforms, AI Model Intergration, Orchestration, Servers, AI Model Training

AI Engineer

2023 - 2024
OctoAI, Inc.
  • Developed POC demonstrating the use of OctoAI's cloud generative AI (GenAI) platform AI for text generation from large-language models (LLMs) and image generation from stable diffusion models.
  • Tested the exclusive OctoAI feature, Asset Orchestrator, that allows fine-tuning of stable diffusion image GenAI by enabling the training of custom weights using a small number of images for a subject.
  • Discovered and documented several OctoAI platform usability issues and responded to requests for my expert opinion on the utility of specific features provided by their GenAI API and WebUI interfaces.
Technologies: Python, PyTorch, Machine Learning, Testing, Natural Language Processing (NLP), Generative Artificial Intelligence (GenAI), Proof of Concept (POC), LoRa, Image Generation, Stable Diffusion, Llama 2, Large Language Models (LLMs), Mistral AI, Algorithms, CSV File Processing, Natural Language Toolkit (NLTK), LangChain, OpenAI, PEFT, Unit Testing, Pytest, pylint, Chatbot, API Management, APIs, Cloud Platforms, AI Model Intergration, Containerization, Orchestration, Servers, AI Model Training

Senior Machine Learning Engineer

2022 - 2023
LiveView Technologies
  • Applied research and development of artificial intelligence and machine learning algorithms for detecting anomalous behavior and events in live-streaming video.
  • Worked on the R&D to deploy artificial intelligence and machine learning capability on NVIDIA Orin edge devices.
  • Led business case and acquisition of hardware and services, including providing $150,000 for Lambda Labs Hyperplane GPU Server with multiple NVIDIA A100 GPUS and acquiring contract services for video annotation for AI/ML training data.
Technologies: Machine Learning, Artificial Intelligence (AI), Computer Vision, Anomaly Detection, Edge Compute, PyTorch, NVIDIA Jetson, RAPIDS, Object Detection, Deep Learning, Predictive Modeling, API Integration, Data Science, PostgreSQL, Time Series Analysis, Testing, Object Recognition, Computer Vision Algorithms, OpenCV, Image Processing, Neural Networks, Time Series, Forecasting, Docker, FastAPI, Containerization, Generative Pre-trained Transformers (GPT), Data Modeling, Algorithms, CSV File Processing, Unit Testing, Pytest, pylint, API Management, APIs, Cloud Platforms, AI Model Intergration, Orchestration, Servers, AI Model Training

Machine Learning Software Engineer

2017 - 2018
Greensmith Energy (Acquired by Wärtsilä)
  • Developed the machine learning and analytics software for the simulation and optimized operation of advanced renewable-energy storage systems (Singularityhub.com/2019/07/21/machine-learning-vs-climate-change-ai-for-the-greener-good/).
  • Designed and developed energy market trading optimization algorithms and applications.
  • Designed and developed Greensmith Energy's first real-time energy market trading process that makes use of advanced optimization models. Ran the models through a 30-day operational test with Électricité de France, the world's largest producer of electricity (En.wikipedia.org/wiki/Électricité_de_France).
  • Designed and developed an energy analytics framework, including energy management optimization, machine learning-based forecasting, and simulation services.
  • Proposed and led design, acquisition and, implementation of Greensmith Energy's largest software acquisition for embedded enterprise and reseller licenses of Gurobi Optimization and Mathematical Solver into Greensmith's Energy Management and Control System (GEMS), CD/CI pipeline, and GEMS Cloud and remote customer deployments.
Technologies: Gurobi, NumPy, Pandas, Scikit-learn, Python, Amazon S3 (AWS S3), Predictive Modeling, Algorithmic Trading, API Integration, Data Science, PostgreSQL, Time Series Analysis, Testing, Artificial Intelligence (AI), Neural Networks, Time Series, Forecasting, Docker, FastAPI, Containerization, Data Modeling, Algorithms, CSV File Processing, Unit Testing, Pytest, pylint, API Management, APIs, Cloud Platforms, AI Model Intergration, Orchestration, Servers, AI Model Training

Senior Software Engineer | Business Intelligence Specialist

2005 - 2013
Independent Consultant
  • Developed for various federal, DoD, intelligence communities, and Fortune 500 companies as an enterprise software engineer and business intelligence consultant.
  • Provided expertise on a variety of data extraction methods that would facilitate the State of New York's compliance with Hearst's FOIA request. I was the expert technical witness for Hearst Publishing in Hearst vs. State of New York (Casetext.com/case/hearst-v-state-of-ny).
Technologies: Tableau, Python, Java, Time Series Analysis, Testing, Neural Networks, Time Series, Forecasting, Data Modeling

Active Learning Research: Department of Computer Sciences at George Mason University

Active learning is a special case of machine learning in which a learning algorithm is able to interactively query the user (or some other information source) to obtain the desired outputs at new data points. In statistics literature, it is sometimes also called optimal experimental design. [Wikipedia: https://en.wikipedia.org/wiki/Active_learning_(machine_learning)]

Renewable Energy Market Trading Optimization

Designed and developed Greensmith Energy's first real-time energy market trading process that makes use of advanced optimization models. Successful 30-day operational test by the world's largest producer of electricity, Électricité de France (EDF: https://en.wikipedia.org/wiki/Électricité_de_France) in a CAISO five-minute real-time energy market simulator. [https://en.wikipedia.org/wiki/California_Independent_System_Operator]

Languages

Python, Java, C++

Libraries/APIs

OpenCV, SpaCy, Natural Language Toolkit (NLTK), Scikit-learn, Pandas, NumPy, PyTorch, Keras, TensorFlow, RAPIDS

Tools

Jupyter, Pytest, pylint, Git, GitHub, Tableau, Gurobi, PyCharm, IntelliJ IDEA, Amazon SageMaker, NVIDIA Jetson

Paradigms

Data Science, Testing, Unit Testing, Agile, Object-oriented Programming (OOP), Linear Programming, Anomaly Detection

Platforms

Docker, Amazon Web Services (AWS), Databricks, Google Cloud Platform (GCP)

Storage

Amazon S3 (AWS S3), PostgreSQL

Other

Machine Learning, Predictive Analytics, Predictive Modeling, Data Analytics, Model Validation, Artificial Intelligence (AI), Computer Vision, API Integration, Time Series Analysis, Object Recognition, Computer Vision Algorithms, Image Processing, Neural Networks, Time Series, Forecasting, FastAPI, Containerization, Data Modeling, Algorithms, Data Matching, CSV File Processing, Transformer Models, Graphics Processing Unit (GPU), SOLID Principles, Bokeh, Optimization, Mixed-integer Linear Programming, Object Detection, Deep Learning, AI Programming, Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNNs), Algorithmic Trading, Natural Language Processing (NLP), Generative Pre-trained Transformers (GPT), OpenAI, PEFT, Abstract Syntax Trees (AST), Chatbot, API Management, APIs, Cloud Platforms, AI Model Intergration, Orchestration, Servers, AI Model Training, Amazon Machine Learning, Google Cloud Machine Learning, Edge Compute, Generative Artificial Intelligence (GenAI), Proof of Concept (POC), LoRa, Image Generation, Stable Diffusion, Llama 2, Large Language Models (LLMs), Mistral AI, LangChain

2014 - 2017

Master of Science Degree in Data Analytics Engineering

George Mason University - Fairfax County, Virginia, USA

2014 - 2015

Graduate Certificate in Predictive Analytics

University of California at Irvine - Irvine, California, USA

1987 - 1993

Bachelor of Science Degree in Computer Science

University of Maryland at College Park - College Park, Maryland, USA

Collaboration That Works

How to Work with Toptal

Toptal matches you directly with global industry experts from our network in hours—not weeks or months.

1

Share your needs

Discuss your requirements and refine your scope in a call with a Toptal domain expert.
2

Choose your talent

Get a short list of expertly matched talent within 24 hours to review, interview, and choose from.
3

Start your risk-free talent trial

Work with your chosen talent on a trial basis for up to two weeks. Pay only if you decide to hire them.

Top talent is in high demand.

Start hiring