I'm an AI engineer and engineering leader. I build and ship AI products in industry, and I research the hard problems in LLMs: hallucination, metacognition, and model architecture.
- Focused on LLM reliability: hallucination, metacognition, and model architecture
- MSc in Generative AI, University of Exeter. My research asks whether language models can recognise the limits of their own knowledge
- Founded and led engineering teams, architecting AI systems from voice agents to data platforms
- Building with Python, Go, Java, and C/C++
- Open to collaboration on AI, backend, and systems projects
- Reach me on LinkedIn or at waqaskhan137@gmail.com