Eric Yates, Developer in Denver, CO, United States
Eric is available for hire
Hire Eric

Eric Yates

Verified Expert  in Engineering

Software Engineering Developer

Location
Denver, CO, United States
Toptal Member Since
January 29, 2019

Eric brings proven expertise as an AI engineer with a specialization in NLP. He has set the state-of-the-art accuracy for de-identification of medical records. He combines machine learning with software engineering for production-ready code. He thrives in collaboration with data scientists, web developers, project managers, legal counsel, and executive management teams.

Availability

Part-time

Preferred Environment

Git, Jupyter Notebook, Atom

The most amazing...

...NLP model I've ever built achieved 98.2% dev F1-score. That beat the previous state-of-the-art.

Work Experience

Machine Learning Engineer

2018 - 2019
Emphasis AI
  • Designed an NLP algorithm with 95% test accuracy.
  • Deployed the NLP algorithm via a RESTful API to a production environment on Digital Ocean.
  • Created an automated testing suite to regularly assess algorithmic performance.
  • Worked with a full-stack developer to improve the reliability of the web application.
  • Collaborated with founder and patent attorney on a provisional patent.
Technologies: GPT, Natural Language Processing (NLP), Generative Pre-trained Transformers (GPT), Django, Python

Machine Learning Engineer

2017 - 2019
Medley
  • Beat state-of-the-art for de-identification of medical records with a 98.2% dev F1-score.
  • Trained a neural network for named entity recognition.
  • Deployed the de-identification model to a production environment with Flask, Nginx, and Gunicorn.
  • Collaborated with a full-stack developer to build a search engine for medical records.
  • Automated build processes with bash scripting.
Technologies: Flask, SpaCy, GPT, Generative Pre-trained Transformers (GPT), Natural Language Processing (NLP), Python

Machine Learning Engineer

2018 - 2018
Independent Contractor
  • Built an end-to-end pipeline for making machine learning predictions.
  • Estimated to allow the liquidation of $750,000-$1.25 million per month.
  • Collaborated with a data scientist to integrate with a scraper and database system.
  • Used Keras to build and train deep neural networks.
  • Deployed the model to a RESTful API with Flask on a Digital Ocean server.
Technologies: Flask, Keras, Scikit-learn, Python

Co-Founder/Software Developer

2015 - 2017
Lexi
  • Created a prototype software-defined radio for ZigBee and 2G protocols.
  • Performed system administration with Linux and bash scripting.
  • Interfaced hardware and software with GNURadio.
  • Collected environmental data using sensors with Arduino.
  • Performed customer discovery for the Illinois NSF I-Corps Program.
Technologies: Bash, Arduino, Linux

Anoni - De-Identification of Medical Records

https://github.com/medra-labs/anoni
Removes protected health information (PHI) from free text in medical records. Achieved 98.2% dev F1-score, which is state-of-the-art, by fine-tuning BERT large on a distributed GPU cluster.

Voice User Interface

Built a voice user interface with a chatbot built into a browser.

Machine Learning From Scratch

https://github.com/eric-yates/Machine-Learning-from-Scratch
Built 12 machine learning algorithms in Python from scratch. Derived a recursive backpropagation algorithm for a neural network.

Languages

Python, Bash, SQL, R

Libraries/APIs

Pandas, Scikit-learn, Keras, SpaCy, NumPy, Natural Language Toolkit (NLTK), Matplotlib, TensorFlow

Paradigms

Object-oriented Programming (OOP), Functional Programming

Platforms

Linux, Jupyter Notebook, Arduino

Other

Machine Learning, Natural Language Processing (NLP), Deep Learning, Software Engineering, Data Visualization, Mixed Reality (MR), Software Development, GPT, Generative Pre-trained Transformers (GPT), Deployment, APIs, Gunicorn

Frameworks

Flask, Django

Tools

Seaborn, Atom, Git, NGINX

Storage

PostgreSQL, MySQL

2011 - 2016

Bachelor of Science Degree in Mechanical Engineering

University of Illinois Urbana-Champaign - Illinois

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