ABOUT ME
My name is Siddharth Satpathy, and I am a senior member of technical staff for AI battery algorithms at Element Energy, California.
Before joining Element Energy, I worked in machine learning engineer positions at Deepfence and Cisco. I hold a PhD in astrophysics from Carnegie Mellon University, Pittsburgh (CMU), a master's in machine learning (ML) from CMU, a master’s in physics from CMU, and another master’s in physics from the National Institute of Science Education and Research (NISER), India.
In Deepfence, I designed machine learning platforms for the detection of anomalies in network communication in cloud computing services. I also built FlowMeter, which is a widely used open-source AI tool (>1000 GitHub stars) that analyzes and sorts network packet captures using machine learning. .
At Cisco, I was part of the team that developed Cisco's Predictive Networks, which enabled the forecasting of user experience in networks.
During my time at Carnegie Mellon University, I built a semi-supervised deep learning architecture for diabetic retinopathy (DR) detection from retinal fundus images in a dataset put together by three hospitals in France.
My PhD research at CMU involved the investigation of the large-scale structure of our universe and the evidence of dark energy. Here, I used deep learning architectures to classify images from telescopes and uncover evidence of dark energy. Additionally, I also developed estimators to probe large datasets of galaxies and quasars to extract information about the structure and evolution of our universe. NASA put out a press release about one of my important pieces of work, which showed how NASA's Nancy Grace Roman Space Telescope could look back in time to see where sound waves from the early universe left marks.
As a part of my master's in machine learning, I also worked on industry-relevant projects, which include but are not limited to the detection of diabetic retinopathy from images of retina scans, identification of electrical components in printed circuit boards, imputation of missing data in Facebook networks, and clustering of cells based on genetic data. These projects have given me both depth and breadth of experience in different facets of machine learning, including deep learning, computer vision, anomaly detection, clustering, and natural language processing.