I am a full Stack Senior Software Engineer
AI model evaluation is the systematic process of assessing an artificial intelligence or machine learning model's performance, reliability, and suitability for its intended task. It involves comparing a model's predictions against a "ground truth" (known correct outcomes) using various quantitative metrics and qualitative assessments.
Specialised in designing and refining high-precision instructions (prompts) and managing the broader 'information ecosystem' (context) that guides Large Language Models (LLMs). I focus on reducing hallucinations and improving output reliability by implementing advanced techniques like Chain-of-Thought and RAG (Retrieval-Augmented Generation). My approach ensures AI agents have the right data at the right time to perform complex, multi-step tasks with professional-grade accuracy.
Versatile Full Stack .NET Developer with a passion for building scalable, end-to-end web applications. I specialise in crafting dynamic front-ends with Angular and robust, high-performance back-ends using C#, .NET Core, and .NET Framework. With a deep understanding of SQL data management and API design, I bridge the gap between complex server-side logic and intuitive user experiences. I thrive in collaborative, agile teams and am constantly evolving my toolkit to stay ahead of the tech curve.