Research
Academic interests and technical research contributions.
Research Interests
Reinforcement Learning from Human Feedback
Optimizing large language model alignment through preference-based learning and reward modeling.
LLM System Design
Infrastructure for scalable inference, prompt engineering, and model evaluation frameworks.
AI System Evaluation
Metrics for reliability, safety, and performance in production AI deployments.
Digital Public Infrastructure
Open systems for identity, payments, and data exchange at population scale.
Academic Profile
ORCID iD
0009-0005-7341-7856
Current Focus
Currently exploring the intersection of AI safety and practical system deployment. Interested in collaborative research on evaluation frameworks for generative AI systems and the development of robust training methodologies for domain-specific applications.