I am an MS by Research student in Artificial Intelligence and Data Science specializing in AI Alignment, LLM Evaluations, and Resource-Aware ML Systems. My work focuses on understanding foundation models beyond surface-level performance, emphasizing objective design, optimization behavior, and model reliability.

My research focuses on epistemic reasoning in multi-source conflict resolution and building instrumented benchmarks to measure the accuracy-efficiency trade-offs of foundation models. My current MS thesis explores multi-objective optimization and Pareto-frontier analysis to ensure AI systems remain reliable, grounded, and computationally sustainable at scale.

I have hands-on experience with vision models and ML systems, alongside a solid theoretical grounding in generative modeling, loss formulations, KL-divergence, and ELBO-based objectives, driving research toward robust, resource-aware multimodal and language-based learning systems.