My research focuses on AI safety, transparency, and the social impacts of frontier AI systems. I work across three active research positions and am currently pursuing my first publication at ICLR.
Paid research assistant at Stanford University. I oversee 20+ member deliberations on frontier AI, AI development, and the social impacts of AI systems. I'm also building and deploying an AI-based fact-checker tool to analyze the reliability, quality, and content of democratic deliberations — exploring how AI can strengthen rather than undermine civic discourse.
Research Assistant under Professor Leilani Gilpin at UC Santa Cruz, working on AI safety research. Professor Gilpin's lab focuses on explainability and accountability in machine learning systems.
Selected as a researcher under the 1:1 mentorship of Professor Faisal Nawab (UC Irvine). Researching and benchmarking high-level risks of AI models including self-preservation instincts and misalignment — understanding how advanced AI systems might behave in ways that diverge from human intent.
Param Raval et al. — Algoverse AI Research. Empirical research paper on real-time interpretation of AI agents to improve transparency and safety. Submitted to the International Conference on Learning Representations (ICLR).
Selected as 1 of 16 students from 500+ applicants for the AI4ALL summer program at Stanford HAI. A rigorous, hands-on research program for underrepresented students in AI.