Building Trustworthy Financial AI: Governance, Bias, and Mechanistic Insights

About

Data Phoenix hosts a remote talk on building trustworthy AI systems in finance, covering governance frameworks, bias detection, and how LLMs actually work under the hood.

Why attend

Fabrizio Dimino will walk through mechanistic interpretability and positional bias—practical techniques for understanding what your financial AI models are actually doing. If you're shipping AI in regulated industries, you'll get concrete governance approaches that go beyond compliance checkboxes.

Who

Machine learning engineers, AI product leads, and risk/compliance teams working with LLMs in financial services.