As organizations increasingly deploy AI and machine learning systems into production, testing practices built for static, rule-based software are no longer sufficient. Unlike traditional applications, AI systems learn from data, change behavior over time, and are sensitive to data drift, bias, and feedback loops, making defects harder to detect with conventional test cases. This session presents a practical, experience-driven approach to testing AI systems across the full lifecycle, from model development to live deployment. Drawing on real-world implementations and applied research, the...
Sowjanya Deva
Senior Data Engineer
Code Acuity
Sowjanya Deva is a Data Engineer and AI researcher with expertise in data engineering, machine learning, MLOps, distributed systems, and large language models (LLMs). Her research focuses on scalable AI infrastructure, parameter-efficient fine-tuning, privacy-preserving machine learning, and real-time feature engineering for next-generation AI systems. She is the author of the published paper Privacy-Preserving Customer Segmentation for Scalable Media Optimization in E-Commerce and the paper Scalable Real-Time Feature Engineering Pipelines for Large Language Model Training: A Distributed Systems Approach. Her accepted work, Rethinking MLOps: Building Modular, Serverless Machine Learning Pipelines on AWS, is forthcoming. Sowjanya actively contributes to the AI community as a peer reviewer, editorial board member, hackathon judge, and volunteer mentor, supporting research excellence and innovation in artificial intelligence, data engineering, and analytics.