cv
PhD in Computer Science (UCF, 2020). SWE-RL at Anyscale. Former Research Scientist at Intel Labs. Publications at ICML, ICLR, IJCNN, AAMAS.
Contact Information
| Name | Hassam U. Sheikh |
| Professional Title | Software Engineer – Reinforcement Learning |
| hassamsheikh1@gmail.com |
Professional Summary
Software Engineer on the Reinforcement Learning team at Anyscale, technical owner of RLlib. Former Research Scientist at Intel Labs. PhD in Computer Science from the University of Central Florida.
Experience
-
2025 - present San Francisco
Software Engineer – Reinforcement Learning
Anyscale
Technical owner of RLlib, the industry-standard distributed RL library.
- Stability, performance, and correctness across RLlib’s distributed training and inference stack
- Reliability hardening, benchmark-driven performance engineering, and regression-prevention guardrails at scale
-
2020 - 2024 Remote
Research Scientist
Intel Labs
- Published at ICML, ICLR, IJCNN, and AAMAS on multi-agent RL, ensemble diversity, and intrinsic reward learning
- Led research on minimizing inter-agent communication in cooperative MARL
- Filed patent on system and method for controlling inter-agent communication in multi-agent systems
-
2016 - 2020 Orlando, FL
Graduate Research Assistant
University of Central Florida
- Research on multi-agent reinforcement learning, robust escort teams, and ensemble Q-learning
- Published at AAMAS, COMPSAC, NeurIPS workshop, ICML workshop
Education
-
2016 - 2020 Orlando, FL
PhD
University of Central Florida
Computer Science
- Dissertation: Stability in Multi-Agent Reinforcement Learning via Defensive Escort Teams
- Advisor: Ladislau Bölöni
Skills
Reinforcement Learning (Expert): Distributed RL, Multi-Agent RL, Offline RL, Policy Gradient, Q-Learning, RLlib, Ray
Machine Learning (Expert): Deep Learning, Ensemble Methods, Intrinsic Motivation, PyTorch
Software Engineering (Expert): Python, C++, Distributed Systems, Ray, Docker, CI/CD
Languages
English : Fluent
Urdu : Native speaker