About Me
I’m Varsha, an AI/ML engineer with a strong foundation in deep learning, self-supervised representation learning, and large language models (LLMs). I hold Master’s degrees in Biomedical Engineering from the University of Wisconsin–Madison and Electrical Engineering from IIT Bombay, where I received the Best Master’s Thesis Award.
My industry experience spans roles at Amazon and the healthcare AI startup named nference. At Amazon, I worked as an Applied Scientist, optimizing transformer-based multilingual models for low-latency intent classification across Alexa platforms. At nference, I developed encoder-decoder and YOLOv5-based models for tissue localization in histopathology, enabling ML-powered precision medicine. During my time at UW–Madison, I applied supervised learning to MRI data for predicting treatment response in oncology.
My research has been published in IEEE biomedical imaging conferences (ISBI, BIBE), focusing on contrastive learning, label noise robustness, and self-supervised learning in medical imaging. I’m proficient in Python (PyTorch, TensorFlow) and experienced in statistical modeling, computer vision, and NLP.
I’m passionate about building scalable ML systems that drive real-world impact and am actively seeking opportunities to contribute to fast-paced teams focused on deploying end-to-end AI solutions.