I have hands-on experience in AI evaluation, Generative AI, LLMs, and AI agent development. I currently work as a Freelance AI Evaluator at Meridial.ai, where I evaluate LLM responses for accuracy, relevance, completeness, and instruction-following. Previously, I interned at Grootz, researching AI agents and GenAI tools and building automated workflows using n8n and AI APIs. I also freelanced with Perplexity AI on Comet Browser research, product testing, AI-assisted workflows, and user outreach.
My projects include an Agentic Firewall Guardrail for detecting prompt injection and preventing data exfiltration, a Medical RAG Chatbot using LangChain and FAISS, and a Resume–JD Matcher powered by LLM APIs. My AI security project achieved a 100% attack block rate with 0% false positives across 29 test cases.
My technical skills include Python, SQL, LangChain, RAG pipelines, prompt engineering, LLM evaluation, AI security testing, and workflow automation. I have also led the AI/ML community at Google Developer Group on Campus, organizing technical workshops and supporting peer learning.
I am interested in AI/ML engineering, Generative AI, AI research and development, LLM evaluation, and AI product roles. I enjoy solving practical problems, experimenting with emerging AI technologies, and building reliable solutions that create real-world value. I am looking for opportunities where I can contribute my technical skills, take ownership, and continue learning in a fast-paced team.
