Sreehari A

I’m an entry-level AI/ML Engineer with hands-on experience in Large Language Model (LLM) evaluation workflows and machine learning application development. I focus on prompt optimization, output quality analysis, and building ML-backed applications using Python and modern AI tools.

In my current role as an Analyst – AI/LLM Practice, I evaluate LLM outputs for accuracy, logical consistency, clarity, and safety compliance, and I identify hallucinations, reasoning failures, and chain-of-thought (CoT) errors with structured feedback. I also design adversarial prompts and challenging image-text scenarios to test robustness, and I perform large-scale LLM evaluation and prompt refinement under strict quality and productivity KPIs.