Afshin Oroojlooy
Principal Reinforcement Applied Scientist at Oracle
Bethlehem, Pennsylvania, United States
Summary
👤
Senior🎓
Top SchoolAfshin Oroojlooy is a Principal Reinforcement Applied Scientist with nine years of experience building production-ready optimization and RL systems, currently delivering optimization services on Oracle OCI's generative-AI/Agent team. He has a strong academic grounding with an M.Sc. and Ph.D. in Industrial Engineering and a track record of turning research into engineering: at SAS he designed a C++ general-purpose RL framework and deployed an RL controller for oven temperatures in automotive glass manufacturing. Comfortable in C/C++ and Python, he bridges algorithm design and systems engineering to apply RL across marketing, inventory, routing and industrial control. Based in Bethlehem, PA, he combines rigorous optimization expertise with cloud-scale deployment experience, and brings a rare mix of academic depth and hands-on production delivery.
9 years of coding experience
10 years of employment as a software developer
Doctor of Philosophy (Ph.D.), Industrial Engineering, Doctor of Philosophy (Ph.D.), Industrial Engineering at Lehigh UniversityBachelor of Science (B.Sc.), Industrial Engineering, 3.87 / 4.00, Bachelor of Science (B.Sc.), Industrial Engineering, 3.87 / 4.00 at Isfahan University of TechnologyMaster of Science (M.Sc.), Industrial Engineering, 4.0 /4.0, Master of Science (M.Sc.), Industrial Engineering, 4.0 /4.0 at Sharif University of Technology
Persian, English, Azerbaijani
Stackoverflow
1,386reputation
118kreached
34answers
62questions
Github Skills (138)
parallel10
python10
hyperparameter-optimization10
deep-learning10
automl10
gpu10
ray10
gpu-acceleration10
optimization10
acceleration10
ml10
llm-inference10
numpy10
falcon10
neural-network10
Programming languages (4)
Github contributions (5)
OptMLGroup/DeepBeerInventory-RL
Jun 2020 - Jun 2021
The code for the SRDQN algorithm to train an agent for the beer game problem
Contributions:22 commits, 19 pushes in 11 months
multiagent-reinforcement-learningstable-baselinesinventory-managementdeep-reinforcement-learningsupply-chain-management
oroojlooy/newsvendor
Jul 2019 - Sep 2020
Contributions:8 commits, 6 pushes, 1 branch in 1 year 2 months
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.