Partner with us

Get your ticket

Call to action

Your text goes here. Insert your content, thoughts, or information in this space.

Button

Back to speakers

Hardik

Nahata

Staff ML Engineer

PayPal

Hardik Nahata is a Staff Machine Learning Engineer at PayPal, where he is spearheading the development of the AI/ML platform infrastructure for real-time, AI-driven shopping experiences, serving millions of PayPal merchants globally. With expertise in Generative AI, Personalization, and Natural Language Processing, he specializes in building scalable machine learning systems that power intelligent automation at scale. Previously, he played a pivotal role at Chegg, where he developed multi-agent LLM systems and Retrieval-Augmented Generation (RAG) architectures to enhance student learning engagement. His work spans cutting-edge applications such as conversational AI, personalized learning pathways, and real-time AI models that drive meaningful user interactions. Beyond his contributions to FinTech and EdTech, Hardik's experience extends across Healthcare and Supply Chain industries, where he has built recommendation engines, NLP-driven content optimization models, and AI solutions that enhance operational efficiency and innovation. Hardik holds a Master’s degree in Computer Science with a specialization in Artificial Intelligence. Recognized as a Top 1% AI/ML Mentor on TopMate, he combines deep technical expertise with real-world industry perspectives, guiding aspiring and experienced professionals as they navigate the evolving landscape of artificial intelligence.

Button

29 July 2026 11:15 - 11:45

Panel | Traceability and observability in agentic systems

As AI workflows span multiple models, agents, tools, and decision points, understanding what happened, why it happened, and where things went wrong becomes increasingly difficult. Traditional monitoring approaches often provide only a partial view of system behaviour, leaving teams with significant operational blind spots. This panel examines how organizations are building traceability and observability into complex AI systems. We'll discuss approaches to tracking workflow execution, investigating failures, monitoring interactions across components, and improving visibility into increasingly autonomous applications. Attendees will gain practical insights into the tools, techniques, and operational practices helping teams better understand and manage AI systems in production.