“Samiran Roy is a highly skilled Data Scientist at CRED with extensive experience in the fields of optimization and recommendation. Prior to his role at CRED, he was a Co-Founder at a startup where he made significant contributions to the development of AI systems for unstructured document understanding.

With a strong academic background, Samiran holds a Master’s degree from the prestigious Indian Institute of Technology Bombay. During his time at IIT Bombay, he focused on the development of advanced software in the fields of deep learning, reinforcement learning, and computer vision. He also worked on the creation of AI agents for a range of applications, including self-driving cars, robot soccer, Atari games, and Carrom.

Samiran’s MTech thesis was centered on the topic of RL, where he developed a novel MAB framework for autonomous agents to supervise their own training. This work demonstrated Samiran’s exceptional analytical skills and his ability to push the boundaries of what is possible in the field of AI.

Prior to joining CRED, Samiran worked as a Lead Data Scientist at Envestnet Yodlee and also gained valuable experience at Scilab Enterprises. His impressive career trajectory is a testament to his dedication, hard work, and exceptional talent in the field of data science.”

Session: Fine-tuning a Language Model with RLHF