Fazl Barez
AI safety and Interpretability Researcher
With over 5+ years of experience in artificial intelligence research, I specialize in developing advanced yet interpretable machine learning systems. In the past I have consulted with think tanks, charities, educational and financial companies.
Consulting Expertise
- Custom ML solution architecture - Collaborating with organizations to design Safe ML pipelines, ensuring Interpretability, robustness, accuracy, and transparency.
- Model auditing - Performing rigorous assessments of AI systems to identify issues related to bias, interpretability, and ethical risks.
- AI governance and oversight - Advising companies on responsible AI practices and helping craft internal policies and best practices.
I have served as a keynote speaker, panelist, programme chair, reviewer and workshop organiser for conferences including NeurIPS, ICLR, ACL and ICML and ECAI. I have also mentored PhD, MSc and BSc students.