Shivam Chaudhary

Architected a multi-agent LLM system processing 100K+ deals daily across 15 enterprise clients, replacing rule-based logic with insight generation from CRM and engagement data. Built and scaled the LLM engineering function, growing the team from 1 to 5 engineers.

Published a research paper and filed a patent on enhancing foundational models (EVA-02), leveraging 90%+ unlabeled Bosch data to boost performance by ~5%. Built a Vision Assignment Marketplace and deployed an object detector and motion analyzer on a Jetson Nano edge test-bed with ~30 FPS latency.

Engineered a multi-million dollar data pipeline to transfer anomalies from large-scale SQL/RDBMS sources to HBase and Solr for remediation via a ticketing system, improving Data Quality Index (DQI) from ~78 to ~86. Deployed an enterprise-grade OCR solution using NLP and custom algorithms on USP contracts after enhancing image quality via GANs.

Forecasted 6-hour survey response likelihood using time-aware Random Forests, Decision Trees, and DNNs. Addressed class imbalance via SMOTE and custom metrics, achieving 91% efficacy on responsive marketing panels.

B.Tech in Mechanical Engineering with a minor in Intelligent Systems from the Indian Institute of Technology, Mandi.