Ttanvi Tummapudi

About

Data scientist/researcher who has built two multimodal LLM systems: an AI-assisted medical triage pipeline using GPT-4o vision + RAG with confidence-scored red/yellow/green outputs, and a master’s project on multimodal cyberthreat detection combining multiple models and using TinyLlama to generate human-readable risk reports. Also partnered with business analysts at Sanvar Technologies to deliver a churn prediction pipeline and Tableau dashboard for decision-making.

Experience

Education

Key Strengths

• Built multimodal LLM triage system using GPT-4o vision + RAG with confidence-scored labels
• Latency optimization via hybrid model setup (o4-mini + GPT-4o) and input sampling/resizing
• Improved reliability/consistency using structured prompts and confusion-based fusion between vision and rules
• End-to-end multimodal cyber threat detection integrating multiple models/datasets with consistent embedding pipeline
• Translated ML outputs into business-friendly segments and delivered decision dashboards (Tableau) for churn prediction