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

Rajesh

Mavi

Technology Lead

Bank of America

Rajesh Mavi is a Senior Lead Data Engineer with 13+ years of experience building large-scale distributed data platforms, real-time streaming systems, and cloud-native analytics solutions across banking, telecom, and enterprise domains. He specializes in Kafka, Apache Spark, PySpark, AWS, Snowflake, Databricks, and Hadoop modernization. Currently at Bank of America via Infosys, he leads Hadoop-to-PySpark migration, enterprise event streaming initiatives, and data quality and governance frameworks. He has delivered scalable ETL systems, fraud analytics pipelines, and AI-enabled RAG architectures. He holds a Master’s in Data Science and is passionate about building reliable, AI-ready data platforms and optimising distributed systems for performance, scalability, and resilience.

Button

19 August 2026 12:15 - 13:00

Panel | Eval in the wild: What actually breaks when you test agentic AI on real financial data

Eval frameworks that work in research don't always survive contact with production financial data. This session brings together panelists covering what they measure, what they have stopped measuring, how they handle non-determinism at scale, and what broke before they got it right. What this session will cover: - Why standard benchmarks fail on production financial datasets - How teams are handling non-determinism in multi-step agent pipelines - Observability tooling being used in live financial environments - What good eval hygiene looks like six months into production Bring your own war stories, this one tends to turn into a comparison of notes.