Summary
Gandharv Patil is an applied scientist and PhD candidate at McGill/Mila with a decade of experience bridging reinforcement learning, probabilistic inference, and control systems. He has contributed to industry-leading research teams at Amazon, Google DeepMind, Microsoft and RBC Borealis, focusing on model-based multi-agent RL, LLM reasoning for external tool use, causal inference and uncertainty quantification. His background in electronic and control engineering informs practical simulation and co-simulation workflows for deploying RL-based controllers and powertrain algorithms. At Mila he developed stochastic approximation methods that underpin scalable RL research, and his internships reveal a pattern of moving theoretical advances toward real-world systems. Based in Toronto, he combines deep academic training with applied research instincts and a knack for interdisciplinary problems spanning ML, controls and probabilistic modeling.
10 years of coding experience
7 years of employment as a software developer
grade 10 Science, grade 10 Science at Rosary High School
Bachelor of Engineering (B.E.) Electronics and Telecommunication, Bachelor of Engineering (B.E.) Electronics and Telecommunication at Savitribai Phule Pune University
Doctor of Philosophy - PhD Artificial Intelligence, Doctor of Philosophy - PhD Artificial Intelligence at McGill University
German, English