About Me
I'm a software engineer with a deep interest in generative AI, search, and evaluation systems. I'm especially drawn to how LLMs interact with retrieval, how relevance is measured, and how to design feedback loops that improve model quality over time.
I enjoy building the tooling, pipelines, and experimentation frameworks that help teams understand whether AI systems are actually getting better—or just getting different.
On the day-to-day, my work touches areas like:
- GenAI + Copilot experiences
- Search and retrieval models
- Evaluation frameworks and metrics
- Model experimentation, A/B testing, and quality analysis
Overall, I'm motivated by the engineering and research challenges that make AI systems reliable, interpretable, and grounded in real-world usage.