Evaluating AI Systems Beyond Accuracy | SFO Meetup | QA

Evaluating AI Systems Beyond Accuracy | SFO Meetup | QA

Get ready to connect, learn, and share experiences with fellow testers in the community.

By The Test Tribe

Date and time

Location

1631 N First St suite 200

1631 North First Street #suite 200 San Jose, CA 95112

About this event

  • Event lasts 2 hours

The Test Tribe 3rd San Francisco Meetup – Evaluating AI Systems Beyond Accuracy

As AI becomes embedded in more business-critical applications, how do we ensure it's not just accurate - but also safe, fair, and understandable?

Join us at The Test Tribe’s 3rd San Francisco Meetup for a session that goes beyond traditional QA metrics and dives into what it really means to evaluate AI systems in today’s world. Led by Radhika Naik, this talk will explore the next frontier of QA for AI: robustness, fairness, and explainability.

Event Details

  • Date: 27th August 2025
  • Time: 6:00 PM – 8:00 PM PDT
  • Venue: 1631 North First Street, Suite 200, San Jose, CA 95112

Session Topic - Evaluating AI Systems Beyond Accuracy: Robustness, Fairness, and Explainability

Session Overview

As AI systems - especially large language models (LLMs) - are increasingly adopted across domains like finance, healthcare, and enterprise platforms, measuring their performance goes far beyond just accuracy.

In this session, Radhika will present a practical QA lens to evaluate AI systems across three crucial dimensions:

  • Robustness – How well does the system hold up under edge cases, adversarial prompts, or unexpected inputs?
  • Fairness – Can the model be trusted to avoid bias and unethical outcomes in high-stakes scenarios?
  • Explainability – Are we able to understand why a model made a particular decision, and can we communicate that clearly to stakeholders?

Key Takeaways

  • A practical QA framework for testing robustness, fairness, and explainability
  • Tools and techniques testers can use without deep ML knowledge
  • Why traditional QA approaches need to evolve for AI-centric applications

This topic aims to empower QA professionals to not just test but trust AI systems by adding ethical and safety layers to the evaluation process.

About the Speaker

Radhika Naik is a Quality Engineering Leader at Apexon, with 16+ years of experience driving enterprise QA transformations and scaling automation across global teams. She specializes in continuous testing, quality strategy, and embedding QE into DevOps pipelines. Radhika has led successful quality initiatives in fintech, health tech, and SaaS, delivering faster release cycles without compromising on product stability.

Radhika is passionate about creating inclusive, collaborative QE teams that embrace innovation, tooling, and process excellence. Her leadership approach is rooted in coaching, metrics-driven decision-making, and enabling teams to own quality from day one.

Why You Should Attend

  • Learn how to evolve your QA strategy for the AI era
  • Gain actionable tools to evaluate complex systems without needing to be an ML expert
  • Understand how fairness, robustness, and explainability fit into a modern QA mindset
  • Connect with the Bay Area’s quality and testing community

If you’re a QA professional looking to stay ahead of the curve as AI reshapes the industry - this is a session you don’t want to miss.

About The Test Tribe

​The Test Tribe is the world’s largest software testing community, empowering global testers since 2018. With over 400+ events, 120K+ members across 130+ countries, we foster collaboration, upskilling, and career growth through expert courses, membership programs, cohorts, and community events.

By RSVPing this event, you agree to have read our Terms and Conditions and the Privacy Policy and also agree to be contacted by us and BrowserStack, with whom we are collaborating for this event.

In the age of AI, QA is more than just validation - it’s a safeguard. Let’s elevate how we test, together.

We’ll see you there!

Organized by

Free
Aug 27 · 6:00 PM PDT