talk-data.com talk-data.com

Mehrnoosh Sameki

Speaker

Mehrnoosh Sameki

2

talks

Principal Product Lead Microsoft

Mehrnoosh Sameki leads AI evaluation science, governance, redteaming, and safety within Azure AI Foundry at Microsoft. Her work focuses on building responsible, scalable tools to help customers assess and govern generative AI and agentic systems, with a strong emphasis on safety and security. She has cofunded open-source tools in the Trustworthy AI space, including Fairlearn, Error Analysis, and the Responsible AI Toolbox, and was recognized in the 2024 Brilliant Women in AI Ethics list. She teaches with Break Through Tech and holds a Ph.D. in Computer Science from Boston University.

Bio from: Microsoft Ignite 2025

Frequent Collaborators

Filtering by: Microsoft Ignite 2023 ×

Filter by Event / Source

Talks & appearances

Showing 2 of 3 activities

Search activities →
Trustworthy AI: Advanced AI risk evaluation and mitigation | BRK113

New challenges and threats are emerging as AI evolves. Learn how Azure AIโ€™s advanced responsible AI tooling, including Azure AI Content Safety and built-in safety tools in Azure AI Foundry like evaluations and monitoring, can help mitigate these risks. This session covers responsible AI tooling announcements from Azure and will equip you with essential strategies and tools for deploying responsible AI applications.

๐—ฆ๐—ฝ๐—ฒ๐—ฎ๐—ธ๐—ฒ๐—ฟ๐˜€: * Sarah Bird * Anna Maria Brunnhofer-Pedemonte * Markus Mooslechner * Mehrnoosh Sameki * Paul Shealy

๐—ฆ๐—ฒ๐˜€๐˜€๐—ถ๐—ผ๐—ป ๐—œ๐—ป๐—ณ๐—ผ๐—ฟ๐—บ๐—ฎ๐˜๐—ถ๐—ผ๐—ป: This is one of many sessions from the Microsoft Ignite 2024 event. View even more sessions on-demand and learn about Microsoft Ignite at https://ignite.microsoft.com

BRK113 | English (US) | AI

MSIgnite

Evaluating and Designing Responsible AI Systems for The Real World | BRK204H

Join us to explore strategies for Responsible AI (RAI) systems and learn how to implement them in your organization. Gain insights into how Microsoft built Bing and prompt flow, our evaluation processes and other emerging tools and practices. Delve into effective prompt and metaprompt design, Azure AI Content Safety, how to prevent jailbreaks and against copyrighted material emissions, and Snippy. We will also discuss our White House commitments with RAI experts.

To learn more, please check out these resources: * https://aka.ms/Ignite23CollectionsBRK204H * https://info.microsoft.com/ww-landing-contact-me-for-events-m365-in-person-events.html?LCID=en-us&ls=407628-contactme-formfill * https://aka.ms/azure-ignite2023-dataaiblog

๐—ฆ๐—ฝ๐—ฒ๐—ฎ๐—ธ๐—ฒ๐—ฟ๐˜€: * Apurva Gala * Mehrnoosh Sameki * Sarah Bird * Catherine Brown * Mallory Monsma * Ed Donahue * Katelyn Rothney * Deb Adeogba

๐—ฆ๐—ฒ๐˜€๐˜€๐—ถ๐—ผ๐—ป ๐—œ๐—ป๐—ณ๐—ผ๐—ฟ๐—บ๐—ฎ๐˜๐—ถ๐—ผ๐—ป: This video is one of many sessions delivered for the Microsoft Ignite 2023 event. View sessions on-demand and learn more about Microsoft Ignite at https://ignite.microsoft.com

BRK204H | English (US) | AI & Apps

MSIgnite