Maria Lungu
Maria Lungu is a software engineer at Algolia with eight years of experience across financial services and AI-powered search. Her work has evolved from frontend and UX into fullstack and data engineering, and she currently focuses on building and understanding agentic systems. She is particularly interested in the human side of AI: what these systems get right, what they get wrong, and how to tell the difference.
Sessions
What Gets Retrieved Gets Reinforced: Gender Bias in Agents
Talk
16. September 2026, 14:35 - 14:55
Main Stage
If your AI agent treats Sarah and Michael differently for the same query, would you know? We built a two-layer detector, learned why retrieval counting drowns in catalog noise, and landed on counterfactual testing as the only reliable signal. You will leave with a concrete, practical approach to testing gender bias in your own agentic systems.