Khaled Ahmed

News:

👉 Checkout my new blog on formal verification of AI outputs, semantics and systems.
Our paper on using LLMs to evaluate behavioral models received the distinguished paper award at Models 2025.

Research Engineer at Huawei Canada, Waterloo: Formal methods and verification of generative large language models.
Ph.D. in Electrical and Computer Engineering from the University of British Columbia, Vancouver: Static and dynamic program analysis, security analysis, and malware detection.
M.Sc. and B.Sc. in Electrical Engineering from Alexandria University, Egypt: FPGAs, computer architecture, and high-level synthesis.

☝️ Check the navigation bar above for more!

The 64.41 Ceiling: What AlphaEval Actually Measures (and Why Every Agent Eval Hits a Wall) by Khaled Ahmed, PhD

Why production environments shatter lab benchmarks, and how to fix your evals.

✋ Before you leave, checkout this website, lots of cool info.