CV

Education

University of Connecticut, Storrs, Connecticut, USA

• Ph.D. in Computer Science and Engineering (August 2022 – present)
• M.S. in Computer Science and Engineering (awarded May 2026)

Bangladesh University of Engineering and Technology (BUET), Dhaka, Bangladesh

• B.Sc. in Computer Science and Engineering (2014 – 2018)

Research Expertise

Record linkage and entity resolution; large-scale data integration; string algorithms; GPU computing; parallel and distributed algorithms; high-performance computing; computational optimization; blocking and candidate generation; cluster quality evaluation; distributed quantum computing.

Research Experience

Graduate Research Assistant, Applied Algorithm Laboratory, School of Computing, University of Connecticut (August 2022 – present)

• Research on scalable record linkage, entity resolution, string algorithms, and high-performance computing for large-scale data integration.
• Developed a linear-time algorithm (O(l₁ + l₂)) for the Jaro similarity metric, improving on its classical quadratic-time formulation.
• Developed bit-parallel and GPU-accelerated record-linkage algorithms that process millions of records and billions of candidate comparisons, achieving more than 100× end-to-end speedup over the CPU baseline.
• Developed GPU string-similarity algorithms achieving approximately 381×–702× speedup over CPU implementations in isolated similarity-computation experiments.
• Designed scalable blocking, pruning, and candidate-generation techniques that reduce the computational cost of large-scale record linkage while preserving matching accuracy.
• Developing cluster-quality metrics and optimization techniques for evaluating and improving record-linkage results, including identifying erroneous assignments in noisy and incomplete data.
• Designing parallel algorithms for GPU and multicore architectures, including workload scheduling, persistent GPU kernels, shared-memory optimization, and parallel similarity computation.
• Research on communication-efficient distributed quantum computing, including optimized communication strategies for the Quantum Fourier Transform and Grover’s search.

Federally Supported Research

U.S. Census Bureau–University of Connecticut Cooperative Agreement (Award No. CB21RMD0160003)

• Research contributor to a cooperative agreement on computational methods for large-scale record linkage and data integration.
• Collaborate with University of Connecticut and U.S. Census Bureau researchers on scalable methods for linking and evaluating large administrative datasets.

Publications

1. Basak, J., Shah, N., Mathur, A., Hutnick, J. A. L., Park, K., Weinberg, D., Sahni, S., and Rajasekaran, S. (2026). “Using Cluster Quality Metrics for Record Linkage Evaluation.” 14th International Conference on Computational Advances in Bio and Medical Sciences (ICCABS 2026). Accepted and presented; forthcoming in Springer proceedings.
2. Basak, J., Shah, N., Haase, K., Mathur, A., Park, K., Steorts, R., Weinberg, D., Sahni, S., and Rajasekaran, S. (2026). “Fast Algorithms for Computing Jaro Similarity.” Journal of Computational Biology.
3. Shah, N., Patiyara, S., Basak, J., Sahni, S., Mathur, A., Park, K., and Rajasekaran, S. (2025). “Efficient Record Linkage in the Age of Large Language Models: The Critical Role of Blocking.” Algorithms.
4. Shah, N., Basak, J., Sahni, S., Mathur, A., Park, K., Weinberg, D., and Rajasekaran, S. (2025). “Double Metaphone Blocking: An Innovative Blocking Approach to Record Linkage.” International Symposium on Bioinformatics Research and Applications (ISBRA).
5. Basak, J., Wang, B., and Rajasekaran, S. (2025). “Problem Specific Communications in Distributed Quantum Computing.” IEEE International Conference on Quantum Communications, Networking, and Computing (QCNC).
6. Shah, N., Soliman, A., Basak, J., Sahni, S., Haase, K., Mathur, A., Park, K., Weinberg, D., White, J., and Rajasekaran, S. (2024). “The Soundex Blocking: A Novel Blocking Approach for Record Linkage.” IEEE International Conference on Big Data.
7. Basak, J., Sahni, S., and Rajasekaran, S. (2023). “SuperBlocking: An Efficient Blocking Technique for Record Linkage.” IEEE International Conference on Big Data.
8. Deo, N., Basak, J., Soliman, A., Weinberg, D., Steorts, R., and Rajasekaran, S. (2023). “Novel Blocking Techniques and Distance Metrics for Record Linkage.” International Conference on Information Integration and Web Intelligence (iiWAS).
9. Basak, J., Soliman, A., Deo, N., Haase, K., Mathur, A., Park, K., Steorts, R., Weinberg, D., Sahni, S., and Rajasekaran, S. (2023). “On Computing the Jaro Similarity Between Two Strings.” International Symposium on Bioinformatics Research and Applications (ISBRA).

Manuscripts Under Review

1. Basak, J., Shah, N., Mathur, A., Hutnick, J. A. L., Park, K., Weinberg, D., Sahni, S., and Rajasekaran, S. (2026). “Using Cluster Quality Metrics for Unsupervised Evaluation and Refinement of Record Linkage Clusters.” Journal of Computational Biology, under review.
2. Basak, J., Shah, N., Hutnick, J. A. L., Sahni, S., and Rajasekaran, S. (2026). “Bit-Parallel Jaro Similarity and GPU-Accelerated Record Linkage.” Submitted to the 2026 IEEE International Conference on Big Data (BigData).

Professional Service

• Peer reviewer: Array (Elsevier); Frontiers in Digital Health

Industry Experience

Software Engineer, Samsung Research, Dhaka, Bangladesh (January 2020 – July 2021)

• Migrated and developed Samsung Cloud Service APIs from Tizen OS to Android for Samsung Galaxy wearable devices.
• Developed software components for IoT and wearable systems, including automated sensor logging, device accessibility services, and home-interface modules.
• Contributed to software systems targeting Tizen 5.5 and Android Wear OS.

Teaching

Lecturer, Department of CSE, Eastern University, Dhaka, Bangladesh (January – May 2019)

• Taught Discrete Mathematics, Structured Programming, and the Structured Programming Laboratory (details).

Honors and Awards

• Graduate Research Excellence Fellowship, School of Computing, University of Connecticut (2024, 2025, 2026)
• Dean’s Merit Scholarship for Honors grades, BUET
• Education Board Merit Scholarships, Ministry of Education, Bangladesh (top 1% in national public examinations)

Technical Skills

• Languages: C/C++, Python, Java, R
• High-performance computing: GPU programming, multicore and parallel algorithm design
• Frameworks: TensorFlow, Keras