At IBM Research, I work in Cloud Monitoring and Analytics.
Specifically, I develop out-of-band and non-intrusive monitoring solutions for virtual machines and containers in cloud data centers. Our agentless systems crawler is opensourced, and allows customizable operational visibility for cloud users and admininstrators. The philosophy and history of this project can be found in this blog: Crawl the Cloud Like You Crawl the Web.
I also dabble with operational analytics, security and compliance in the cloud, under the umbrella term 'Vulnerability Advisor', which exists as a service in IBM Bluemix today.
My research interests lie broadly in the fields of Virtualization, Cloud Computing, Parallel & High Performance Computing. My secondary interests include Wireless Networking and Mobile Computing.
I graduated from University of Toronto in 2016 with a Doctorate in Computer Science. My advisor was Eyal de Lara. My IBM Mentor (and now, my Manager!) was Canturk Isci. In my Ph.D. research, I focused on developing non-intrusive and more efficient techniques for virtualization management and virtual systems monitoring.
In the past, I have spent my summers at Microsoft Research Redmond in 2008 (Networking Research Group), Mircosoft Research India in 2011 (Mobility, Networks and Systems Group), and IBM Research T.J. Watson NY in 2012 and 2013 (Virtualization Runtime & Tools Group).
I have a Master's and Bachelor's degree from Indian Institute of Technology, Kanpur (2010). In my Master's research (2009- 2010), I worked towards improving the performance of IO intensive parallel applications by augmenting an advanced pre-execution data prefetching framework with proposed prefetching schemes differing in their aggressiveness- decisions regarding when and how much to prefetch. Maximum prefetching benefits were shown to be obtained for a proposed pre-emptive prefetching scheme that adapts its aggressiveness as per the demands of the application. My advisor was Sanjeev K Aggarwal.
A list of my research contributions can be found here.