AI/ML engineer finishing CS degree, obsessed with RAG pipelines, hybrid search, and LLM orchestration. Currently interning at NeuralVedaX.
Built KinetiAI — a multimodal AI physical therapy assistant that combines pose estimation, voice LLM dialogue, and RAG-grounded clinical responses. 2 IEEE papers submitted.
Targeting a funded Masters in AI/Robotics — Japan, New Zealand, Canada, or Germany. Research output is the north star right now.
Multimodal AI Physical Therapy Assistant for ACL Rehabilitation
End-to-end system combining AR pose estimation, voice LLM dialogue, and FAISS-based RAG clinical grounding. Built for real patients, not demos.
Enterprise-grade retrieval pipeline with multi-strategy fusion
BM25 + FAISS with RRF fusion, cross-encoder reranking, and a unified multi-provider LLM abstraction layer (Anthropic, OpenAI, Gemini). Deployed on Azure VM.
Peer-reviewed work at the intersection of AI and healthcare.
Open to research internships, AI/ML roles, and collaborations.