My business

I work at Amazon Web Services as an Applied Scientist in Redshift DBS group. My work involves cloud workload management and query optimization among others.

During my doctoral studies, I worked in the Duke Database group at the department of Computer Science in Duke university. I was jointly advised by Dr. Shivnath Babu and Dr. Jun Yang. The topic of my dissertation was memory management in data analytics clusters. I followed it up with a postdoctoral research in the Data Analytics group at QCRI working on the problems of data lake management and urban mobility.

Earlier, I did Master's from the Indian Institute of Science, Bangalore. I worked in Database systems lab under the supervision of Dr. Jayant Haritsa on query optimizations in relational databases.

Published papers and select project reports:

M. Kunjir, and S. Chawla, Offline Reinforcement Learning for Traffic Signal Control, ArXiv Preprint, 2022.
S. Thirumuruganathan, M. Kunjir, M. Ouzzani, and S. Chawla, Automated Annotations for AI Data Transparency, Journal of Data and Information Quality, 2021.
B. Xie, Q. Cao, M. Kunjir, L. Wan, J. Chase, A. Mandal, and M. Rynge, WIRE: Resource-efficient Scaling with Online Prediction for DAG-based Workflows , IEEE Cluster, 2021.
M.Kunjir, S.Babu: Black or White? How to Develop an AutoTuner for Memory-based Analytics, SIGMOD Conference 2020: 1667-1683.
M.Kunjir: Speeding up AutoTuning of the Memory Management Options in Data Analytics, Journal of Distributed and Parallel Databases: 38(4), 841-863. (2020).
M.Kunjir: Guided Bayesian Optimization to AutoTune Memory-based Analytics, ICDE Workshops 2019: 125-132.
M.Kunjir, S.Babu: Thoth in Action: Memory Management in Modern Data Analytics, PVLDB 10(11): 1917-1920 (2017).
M.Kunjir, B.Fain, K.Munagala, S.Babu: ROBUS: Fair Cache Allocation for Data-parallel Workloads, SIGMOD Conference 2017: 219-234.
M.Kunjir: Allocating Shared Resources in Multi-tenant Analytics Clusters, CoNEXT Student Workshop, 2015.
M.Kunjir, B.Fain, K.Munagala, S.Babu: ROBUS: Fair Cache Allocation for Multi-tenant Data-parallel Workloads, CoRR abs/1504.06736, 2015.
M.Kunjir, P.Kalmegh, S.Babu: Thoth: Towards Managing a Multi-System Cluster, PVLDB 7(13): 1689-1692 (2014).
M.Kunjir, P.Birwa and J.Haritsa: Peak Power Plays in Database Engines, EDBT 2012: 444-455.

Select talks:

M.Kunjir, J.Lucas: Gearing up for FIFA 2022 using RLlib-powered Traffic Control, Ray Summit, San Francisco, August 2022.
M.Kunjir: Automating Memory Management in Data Analytics, PhD Defense, Duke University, March 2019.
M.Kunjir, S.Babu: Understanding Memory Management in Spark for Fun and Profit, Spark Summit, San Francisco, June 2016.
M.Kunjir, H.Lim: Lightning-Fast Cluster Computing with Spark and Shark, Invited talk, TriHUG meetup, Durham, May 2013.

Reach me at mayuresh<dot>kunjir<at>gmail<dot>com for any details.

Google Sites

Report abuse