Viraj Karambelkar is a NASA Hubble Fellow and PhD astrophysicist with nine years of experience building scalable data pipelines and statistical/ML systems to mine astronomical big data for rare phenomena. At Caltech he engineered a realtime Python pipeline that processes 100 GB of images per night and sifted millions of candidate sources to discover a handful of extremely rare cosmic explosions each year, and his work contributed to over fifty publications including three Nature papers. He combines deep domain expertise in time-series analysis and classification with production-grade engineering—having written observatory automation software in Python and C++ for a robotic telescope and classified variability across tens of millions of stars. Based in Los Angeles, he is motivated to translate these data-science skills to real-world problems that impact people, bringing both a researcher’s rigor and a practitioner’s focus on reliable, automated systems. An unexpected strength is his track record of optimizing pipelines for extreme class imbalance, turning vanishingly rare signals into robust, actionable discoveries.
Contributions:7 PRs, 19 pushes, 12 branches in 1 year 10 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.