Open to opportunities

Shrey Nag

@shreynag

Message

I build AI safety evaluations, LLM auditing systems, and production ML backends.

India

Message

What I'm looking for

I'm targeting AI Safety, Machine Learning Engineering, and Applied Research roles where I can build LLM evaluation frameworks, agent auditing systems, robust benchmarks, and production ML pipelines.

I've built LLM evaluation and auditing systems through the IndiaAI Mission at MeitY, including Inspect India Evals, an India-specific extension of Inspect AI, and AgentAudit, a 10-module framework for auditing agent execution traces. My work evaluates multilingual reasoning, social bias, safeguards, cultural knowledge, fraud, and adversarial attacks across Indian deployment conditions.

At Hughes Systique, I delivered an LLM chatbot evaluation framework that improved response accuracy by 15% and reduced manual document processing by 90%. I also build end-to-end ML products, including a 96% ROC-AUC fraud detection service and RAG-based document Q&A and code-auditing platforms using Python, PyTorch, FastAPI, Docker, and PostgreSQL.

Experience

Work history, roles, and key accomplishments

AI Safety Research Intern

Ministry of Electronics & Information Technology (MeitY), In

Jun 2026 - Jul 2026 (1 month)

Evaluated leading LLM safety frameworks and developed India-specific evaluation modules, including multilingual reasoning and fraud detection. Built AgentAudit, a 10-module auditing framework, and ran 45 model-task evaluations to assess safety and compliance.

Garak Red Teaming Adversarial Testing Benchmark Design LLM As Judge Python PyTorch fastAPI Docker

Education

Degrees, certifications, and relevant coursework

Thapar Institute of Engineering and Technology

Bachelor of Technology, Electronics and Communication Engineering

2023 -

Pursuing a Bachelor of Technology in Electronics and Communication Engineering with coursework in machine learning, data structures, and computer networks.