Shrividya Hegde
Senior AI Data Engineer
New Brunswick, New Jersey, United States
Actions
Shri is an AI Data Engineer with over a decade of experience in automation as an SDET, bringing a strong quality-first mindset to modern data and AI systems. She has deep, hands-on expertise in Apache Airflow–based data platforms, with a focus on building reliable, scalable, and well-orchestrated data pipelines.
An Apache Airflow Champion and Chapter Lead for Women in Data, Shri is also an active technical writer on Medium and Substack, where she shares insights on data engineering and GenAI. Her work centers on helping teams move GenAI initiatives from experimentation to production by emphasizing observability, robust orchestration, and rigorous testing practices.
Links
Badges
Area of Expertise
Topics
Orchestrating and Testing RAG Pipelines with Airflow
RAG pipelines fail silently. Bad retrievals, hallucinated answers, and stale vectors rarely trigger alerts; they quietly degrade your AI product.
This session presents a reference DAG architecture for production-grade RAG ingestion built on Airflow 3, with inline quality gates that evaluate retrieval accuracy and LLM faithfulness before a single vector reaches production. We'll walk through four common RAG failure modes and the specific Airflow pattern that stops each one using RAGAS as the evaluation framework, and Airflow 3's TaskFlow API, Assets, and DAG Versioning to make pipelines reproducible and event-driven.
You'll leave with reusable quality gate patterns and a concrete architecture you can adapt — because in RAG systems, quality shouldn't be an afterthought. It should be built into the pipeline from the start.
Shrividya Hegde
Senior AI Data Engineer
New Brunswick, New Jersey, United States
Links
Actions
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top