Sunil Suresh

Lead fraud and severity data modelling for Allied World's Claims Analytics team across 9,000 Program Business Claims, building signals and features to flag high-risk claims early. Serve as primary technical liaison between data science and business stakeholders, and lead end-to-end transformation of document triage and intervention decisioning.

Led technical vision for platform Data Science and GenAI integration, partnering with Product and Engineering to set engineering standards. Architected end-to-end autonomous decision workflows using GPT, Mistral, and Claude, and designed a conversational RAG-based agentic system for the message composer.

Fine-tuned transformer models including BERT, RoBERTa, and LegalBERT for multi-class NLP tasks such as entity recognition and clause categorisation. Built end-to-end NLP pipelines for structured information extraction from legal document corpora and applied Bayesian probabilistic modeling using Pyro for fraud risk forecasting.

Developed time series forecasting models to predict crop lifecycle events, pest outbreaks, and disease risks using historical and environmental data. Built predictive analytics pipelines integrating weather, satellite imagery, and temporal signals for early warning systems.

Grade: 8.28/10

Bachelor of Technology in Mechanical Engineering with a specialization in Data Science, achieving a GPA of 8.28/10.

Earned the Databricks Certified Machine Learning Associate certification.