Hi, I’m Varsha!

I’m an AI/ML engineer with expertise in deep learning, self-supervised learning, and large language models (LLMs). I hold Master’s degrees in Biomedical Engineering (UW–Madison) and Electrical Engineering (IIT Bombay, Best Thesis Award).

At Wisconsin Reading Center, I am working on building a vision based transformer classification network for early diabetic retinopathy diagnosis. At UW–Madison, I applied feature engineering and supervised learning on MRI data to predict treatment response, advancing AI applications in oncology. At Nference, as Data Scientist, I built encoder-decoder and YOLOv5-based models for tissue localisation and detection in histopathology images, enabling ML-driven precision medicine. At Amazon, as Applied Scientist, I optimised transformer-based multilingual models for low-latency, scalable intent classification across Alexa platforms.

I have co-authored peer-reviewed publications in IEEE biomedical imaging conferences (ISBI, BIBE), focusing on contrastive learning, label noise robustness, and self-supervised learning for medical image analysis.

Technical Skills

  • Programming & Frameworks : Python, PyTorch, TensorFlow, MATLAB, LangGraph
  • Core AI/ML Areas : Deep Learning, Transformers, LLMs, Self-Supervised Learning, Multiple Instance Learning, NLP, Computer Vision, Statistical Modeling, Feature Engineering
  • Domains : Healthcare AI, Precision Medicine, GenAI
I’m passionate about building scalable ML systems that drive real-world impact and am actively seeking Applied Science / AIML Engineer roles to contribute to fast-paced teams focused on deploying end-to-end AI solutions.