I am an applied AI engineer focused on building reliable and interpretable intelligent systems. My work sits at the boundary between research and production, where models meet real-world constraints, imperfect data, and measurable outcomes. I am particularly interested in evaluation, robustness, and system design for large language models.

Research & Engineering Focus

My interests sit at the intersection of applied machine learning and systems.

I work on robust LLM applications, evaluation methodology, retrieval-augmented generation, and scalable deployment architectures. I am particularly interested in how intelligent systems behave under real-world constraints such as noisy data, limited context, shifting distributions, and strict latency or cost requirements.

I aim to build methods that are both scientifically grounded and operationally viable.