Nishant Gurunath

Activities

1

talks

Assc Dir - Machine Learning Moody's

Nishant is a data scientist and ML engineer with 5 years at Moody’s and a Master’s in Computer Engineering from Carnegie Mellon. He specializes in NLP, with experience in information extraction, fraud detection, and recommendation systems. His work spans traditional ML to advanced LLMs, with a focus on Transformer fine-tuning, RAG systems, and AI agents. He led the development of the AI Screening Agent, automating Level 1 KYC workflows with human-level accuracy. Nishant is skilled in Hugging Face, PyTorch, and Databricks, and regularly builds scalable, explainable ML systems on AWS. He is passionate about creating real-world AI solutions that deliver impact.

Bio from: Data + AI Summit 2025

Filter by Event / Source

Data + AI Summit 2025 1

Talks & appearances

1 activities · Newest first

Search activities →

Moody's AI Screening Agent: Automating Compliance Decisions

2025-06-10 · Data + AI Summit 2025 Watch

talk

AI/ML LLM RAG React

The AI Screening Agent automates Level 1 (L1) screening process, essential for Know Your Customer (KYC) and compliance due diligence during customer onboarding. This system aims to minimize false positives, significantly reducing human review time and costs. Beyond typical Retrieval-Augmented Generation (RAG) applications like summarization and chat-with-your-data (CWYD), the AI Screening Agent employs a ReAct architecture with intelligent tools, enabling it to perform complex compliance decision-making with human-like accuracy and greater consistency. In this talk, I will explore the screening agent architecture, demonstrating its ability to meet evolving client policies. I will discuss evaluation and configuration management using MLflow LLM-as-judge and Unity Catalog, and discuss challenges, such as, data fidelity and customization. This session underscores the transformative potential of AI agents in compliance workflows, emphasizing their adaptability, accuracy, and consistency.