Prajjwal is a Research Engineer specializing in AI safety, interpretability, and model evaluations. His current work also focuses on advancing embeddings and AI agents. With a background in AI safety and privacy, he has experience tackling challenges related to federated learning, differential privacy, and machine unlearning. Prajjwal holds a Master’s degree in Artificial Intelligence from Northeastern University, where his research centered on verifiable machine learning and unlearning within federated systems.
Research Areas
AI Safety & Privacy, Interpretability, Applied ML