At Turing, I worked on AI and LLM projects across prompt engineering, domain-expert review, AI quality evaluation, automation testing, and AI engineering. I designed prompts to assess model reasoning, instruction following, accuracy, and robustness.
I also reviewed AI-generated outputs for factual and logical issues, then provided structured feedback to support model improvement. For Turing's CPT tool, I designed and executed automation tests covering workflows, edge cases, and regression scenarios.
At Handshake AI, I worked on Project SEAL, first as a Prompt Engineer and later as an AI Reviewer. I created challenging prompts for large and proprietary LLMs and evaluated responses for correctness, reasoning quality, relevance, and consistency.
At CSDT IT Solutions, I developed software using Python and C++, including the Crop Disease Prediction System for farmers in Bihar. I implemented data preprocessing, model training, and prediction workflows using Random Forest classification.
