I am a Staff Research Scientist & Research Lead at Spotify. My interests are in the field of information retrieval, recommender systems, natural language processing, and machine learning. Prior to Spotify, I was a research staff member at IBM and a postdoctoral fellow at Columbia University. I have a Ph.D. from the University of Delaware and my thesis focused on Novelty & Diversity in Information Retrieval Systems.
8+ years of industry experience in Search, Recommendations, Large-scale Experimentation, and Metric Development. Strong emphasis and strength in translating state-of-art research into practice leading to highly impactful product outcomes. Led projects that spanned across missions and several teams working with data scientists, machine learning specialists, researchers, backend, and data engineers. Helped extensively in the hiring process to build research labs and advocated for inclusivity in hiring. Passionate about learning new technologies and efficient at prototyping ambitious ideas that help bootstrap innovative products.
At Spotify, I’ve led various projects that include: development and implementation of processes to improve machine learning experimentation practices across several teams; high-level design of company-level ML infrastructure technologies such as Spotify Kubeflow; and contributions to the company-wide ML Tech Strategy. Previously, I’ve worked on developing search and conversational AI solutions for meeting scheduling (at X.AI) and health care (at Columbia). At IBM, I focused on the development & implementation of scalable interactive conversational AI agents with a focus on the human-compute-interaction aspects.
I’ve worked on research and published research papers on different topics, including search, recommendations, experimentation, chatbots, and health care. Published >40 research papers at top conferences, such as WWW, SIGIR, WSDM, KDD, NeurIPS, and served as PC/SPC in several conferences.