I work at the intersection of machine learning, deep learning, audio/vision systems. My background includes modern AI system design, with a focus on building practical, scalable, and real-world deployable solutions. My current interests include reinforcement learning, generative modeling, multimodal AI, and perception systems for accessibility and robotics.
I also contribute to applied research, including published work in Audio AI
Mallavolu S., et al. “Audio-visual source separation with localization and individual control.” PLOS ONE, 2025.
DOI: https://doi.org/10.1371/journal.pone.0321856
