Sai Chandra Pandraju

Sai Chandra Pandraju is a Machine Learning Engineer at Red Hat, focusing on making GenAI systems safer, more transparent, and aligned with responsible AI principles. His work spans explainability, robustness, and red-teaming LLMs to ensure they behave as intended—even when prompted otherwise. He specializes in natural language processing, with particular interest in retrieval, representation learning, and language models ranging from compact SLMs to hefty LLMs. He is especially curious about how these models/systems behave under adversarial pressure, and how we can build resilient safeguards that actually hold up.