Ryan Angi
Machine Learning Engineering at Hightouch
Charlotte, North Carolina, United States
Summary
👤
Senior🎓
Top SchoolRyan Angi is a machine learning engineer with nine years of experience building production recommender systems and reinforcement learning frameworks to drive measurable business impact. He specializes in contextual bandits and online decisioning, having architected a scalable RL recommendation API that served 600M decisions per year and generated $15M+ in annual value across major publisher brands. Equally comfortable in Golang and Python, he builds simulation environments (OpenAI Gym-style) to cheaply validate ideas offline and cut live experimentation costs by hundreds of thousands of dollars. Ryan splits his time between software engineering, research, and product ideation, which lets him move from prototype to production quickly while keeping experiments tightly tied to business KPIs. Based in Charlotte, NC, he pairs a mathematical economics background with hands-on ML systems experience to translate complex algorithms into reliable, high-throughput services.
9 years of coding experience
8 years of employment as a software developer
B.S. in Mathematical Economics with a double minor in Statistics and Politics and Int. Affairs, B.S. in Mathematical Economics with a double minor in Statistics and Politics and Int. Affairs at Wake Forest University
English, French, German, Italian
Github Skills (27)
cpp8
active-learning8
bayesian8
reinforcement-learning8
frontier8
statistics7
machine-learning7
python6
marketing6
vowpal-wabbit6
streaming5
breakout5
pytorch4
r-package4
deep-learning4
Programming languages (6)
Github contributions (5)
rangi513/grizbayr
Apr 2020 - Jan 2023
Uses simple Bayesian conjugate prior update rules to calculate metrics for various marketing objectives
Contributions:6 releases, 1 review, 77 commits in 2 years 9 months
statisticsconjugateconjugate-priorupdatemarketing
rangi513/vw-mushroom-go
Jul 2020 - Aug 2020
This is an example of a contextual bandit simulator implementing Vowpal Wabbit's RL framework through a Go interface.
Contributions:4 PRs, 19 pushes, 6 branches in 18 days
golangwabbitoomopenflowreinforcement-learning
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.