Research Scientist specializing in quantized and hardware-aware deep learning for autonomous systems with expertise in model compression (pruning, quantization, knowledge distillation), transformers and LLM optimization, and real-time deployment on embedded platforms (Qualcomm SoCs, NVIDIA Jetson, RTX GPUs). Strong research track record with publications at DATE, DAC, IEEE TCAD, IEEE ICPCSI, and a book chapter on efficient autonomous systems.