Our Team

Meet the researchers, faculty, and students working at the SAFERR AI Lab to advance safe, reliable, and robust AI systems.

Faculty

Prof. Amrit Singh Bedi

Assistant Professor, Lab Director, UCF

Amrit Singh Bedi is a Professor of Computer Science specializing in AI safety and reliability. He has published over 100 papers and received numerous awards for his work on robust AI systems.

Research Interests:

AI safetyReinforcement LearningAI alignment

PhD Students

Avinash Reddy

Ph.D. Student, UCF

Ph.D. student interested in AI alignment and diffusion models.

Research Interests:

AI alignmentReasoningDiffusion models

Soumik Ghosh

Ph.D. Student, UCF

Soumik Ghosh is a Computer Science Ph.D. candidate at UCF researching generative models, diffusion alignment, and responsible AI, with a focus on machine unlearning. He holds a BS-MS in Physics and a PG diploma in condensed matter physics, and enjoys cooking, gardening, photography, and bass guitar.

Research Interests:

Generative ModelsAlignment of Diffusion ModelsSafety in T2I modelsMachine Unlearning

Anirudh Thatipelli

Ph.D. Student, UCF

Ph.D. student interested in AI alignment and diffusion models.

Research Interests:

AI alignmentReasoningDiffusion models

Postdocs

Prashant Trivedi

Post-doctoral Scholar, UCF

Prashant Trivedi is a post-doctoral scholar at UCF working closely with Prof. Amrit Singh Bedi. He received his Ph.D. from IIT Bombay under the supervision of Prof. N. Hemachandra. His research focuses on advancing decision-making under uncertainty, with an emphasis on both theoretical and practical aspects of machine learning, optimization, reinforcement learning (RL), multi-agent systems, and AI alignment.

Research Interests:

Reinforcement Learning (RL)Multi-Agent Reinforcement Learning (MARL)OptimizationAI Alignment

Utsav Singh

Researcher, IIT Kanpur

ML enthusiast trying to decipher and bridge the gap between theoretical machine learning and real-world applications.

Research Interests:

Reinforcement LearningAI AlignmentRoboticsLLMs

Collaborators

Souradip Chakraborty

Ph.D. Student, UMD

Souradip Chakraborty is a Ph.D. student at the University of Maryland focused on developing principled reinforcement learning algorithms to align AI agents in adaptive environments. His work aims to ensure AI systems are safe, robust, and aligned with human behavior.

Research Interests:

Reinforcement LearningAlignmentLanguage ModelsOptimization

Soumya Suvra Ghosal

Ph.D. Student, UMD

I am a Ph.D. student in the CS department at the University of Maryland, College Park. Prior to this, I completed my Master's in Computer Science at the University of Wisconsin-Madison. I am interested in the broad domain of LLM Alignment, and Trustworthy AI.

Research Interests:

LLM AlignmentTrustworthy AI