Abhijeet Krishnan
Research Scientist at Meta
Mountain View, California, United States
Summary
👤
Senior🎓
Top SchoolAbhijeet Krishnan is a research scientist with a PhD in Computer Science from NC State and 11 years of experience at the intersection of machine learning, program synthesis, and player modeling. His doctoral work focused on interpretable strategy synthesis for competitive games, and he builds RL policies as readable programs to bridge game AI and human-understandable strategies. Currently at Meta in Mountain View, he has applied offline RL and decision transformer techniques to synthesize programmatic policies and contributed to TF-Agents, demonstrating practical expertise with a widely used open-source RL library. Past roles span game studios and research labs—extending game-description languages at Zynga, developing gym-style synthesis environments at TCS Research, and researching player mental models at NC State. He combines rigorous academic training with hands-on engineering, from large C++ codebases to scalable simulators, and is especially adept at turning learned behaviors into reusable programmatic artifacts.
11 years of coding experience
1 year of employment as a software developer
Doctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at North Carolina State UniversityBachelor of Technology - BTech, Computer Science, 8.68, Bachelor of Technology - BTech, Computer Science, 8.68 at Visvesvaraya National Institute of Technology
English, Hindi, Tamil, Japanese
Stackoverflow
13reputation
114reached
0answers
1question
Github Skills (10)
machine-learning10
agent10
tensorflow10
ai-agent10
python10
reinforcement-learning10
algorithm9
bandit7
vectorization6
numpy6
Programming languages (12)
Github contributions (5)
tensorflow/agents
Apr 2021 - Apr 2021
TF-Agents: A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning.
Role in this project:
ML Engineer
ML EngineerContributions:7 commits, 1 PR, 7 comments in 13 days
Contributions summary:Abhijeet primarily contributed to the tf-agents library, focusing on environment validation, code formatting, and parameter adjustments within the `environments/utils.py` file. Further contributions involved integrating changes from the master branch and modifying the `BehavioralCloningAgent` and `SacAgent` within the codebase. This work demonstrates an understanding of RL agents and model configuration within the TF-Agents framework.
scalabletf-agentsmultiagent-reinforcement-learningtensorflow-librarymulti-armed-bandits
AbhijeetKrishnan/codebook
Jul 2016 - Jan 2024
Contributions:38 pushes, 11 branches, 7 issues in 7 years 7 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.