student researcher with interests in multimodal/multilingual interpretability, alignment & safety. also: reasoning models, RL, synthetic data, making smaller models better, for democratized ai.
currently research intern at AI4Bharat (visual reasoning, multimodal multilingual interp). previously ai engineer intern at Sarvam AI — built the eval framework for an NVIDIA lipsync model + modularized the dubbing pipeline (video).
i like cracking models open to figure out why they fail, analogous to a neurosurgeon of ai models.
some of the works done with other orgs are not publishable.
→ other — certifications, hackathon wins, skills, smaller builds & awards