Large Language Models
Evaluation of frontier models on complex coding and reasoning tasks, agentic workflows, and human-feedback methods.
About
Ravindra Siva Sai Kumar Medicharla
ML & AI Engineer · Graduate Researcher
I design, train, and deploy end-to-end machine learning systems across computer vision, generative AI, and healthcare AI. I care about model evaluation, explainability, MLOps, and work that holds up outside a demo.
Research interests
Current research interests
Computer Vision
Image restoration, object detection, and semantic segmentation with deep neural networks.
Generative AI
Attention architectures, Vision Transformers, and GAN-based approaches for image generation and translation.
Agentic AI
Reinforcement learning agents, explainable decision-making, and evaluation of AI systems in agentic environments.
Explainable AI
SHAP explanations, Grad-CAM visualizations, and interpretability that builds trust in model predictions.
Production ML
End-to-end pipelines, model deployment, CI/CD for ML, and systems that hold up outside a demo.
AI Trainer — LLM Evaluation
Handshake AI · Remote
Graduate Researcher
AI-CHESS Lab, Saint Louis University
M.S. Artificial Intelligence candidate
Saint Louis University · GPA 3.83
Away from research, I spend time on photography, strength training, music, and writing short notes about what I am learning.
Explore these interests