Summary
Shyam Sundar is a computer scientist and ML researcher with nine years of professional experience, currently pursuing thesis-based graduate work in time series synthetic data generation and anomaly detection at Missouri S&T. He designed a GAN-based unsupervised anomaly detector, scaled it to GPU clusters, and demonstrated a 13% average F1 improvement over prior state-of-the-art across 250 datasets, leading to a PAKDD 2023 full paper. His industry experience includes building end-to-end clickstream ETL pipelines with Python, PySpark and Databricks and optimizing Snowflake costs at Blend360, plus hands-on CV and NLP work implementing R-CNN variants and NER in production-oriented settings. Comfortable bridging research and engineering, he benchmarks models rigorously against many baselines and adapts prototypes for distributed training and real-world data pipelines. Based in Missouri, he combines a strong academic record with practical data engineering chops and a knack for squeezing performance gains out of both models and infrastructure. An under-the-radar strength is his experience evaluating models at scale across hundreds of datasets, revealing robust, generalizable improvements rather than niche wins.
9 years of coding experience
2 years of employment as a software developer
Master of Science - MS, Computer Science, Master of Science - MS, Computer Science at Missouri University of Science and Technology
Anna University, Chennai
English, Tamil