Education

• B.Tech in Computer Science and Technology, Indian Institute of Engineering Science and Technology (IIEST) Shibpur, 2021–2025
  • CGPA: 9.5

Work experience

• May 2026–present: Anthropic Fellow
  • Anthropic Fellows Program
  • Working on AI safety and alignment research
• January 2025–May 2026: Pre-doctoral Research Fellow, Team DiskANN
  • Microsoft Research India
  • Developed learning-based, filter-aware distance metrics for approximate nearest neighbor search (paper)
  • Built WinSyn, an automated synthetic enterprise data pipeline for evaluating agentic Deep Research systems (paper)
• May 2024–July 2024: Software Development Engineer Intern
  • Amazon
  • Implemented domain-driven design principles to optimize the notification triggering process

Publications

Side Effects of Character Training: Quantifying Cross-Constitution Drift in LLMs

Kumar, B., Sutradhar, A., Panigrahi, S., Chang, J., & Levine, L. (2026). "Side Effects of Character Training: Quantifying Cross-Constitution Drift in LLMs." ICML 2026 Workshop on Pluralistic Alignment.

WinSyn: An Automated Pipeline for Realistic Enterprise Question-Answering Evaluation

Varhade, A., Sutradhar, A., Krishnaswamy, R., & Goyal, N. (2026). "WinSyn: An Automated Pipeline for Realistic Enterprise Question-Answering Evaluation." arXiv preprint arXiv:2609.12171.

Learning Filter-Aware Distance Metrics for Nearest Neighbor Search with Multiple Filters

Sutradhar, A., Gupta, S., Krishnaswamy, R., Xu, H., Rastogi, A., & Srinivasa, G. (2025). "Learning Filter-Aware Distance Metrics for Nearest Neighbor Search with Multiple Filters." arXiv preprint arXiv:2511.04073.

Systematic Biomarker Discovery for Glioblastoma Subtyping Using Machine Learning

Sutradhar, A., Banerjee, A., Samanta, A., Hossain, S. F., Dey, A., & Biswas, S. (2025). "Systematic Biomarker Discovery for Glioblastoma Subtyping Using Machine Learning." IEEE INDISCON 2025. pp. 1–6.

Participations

• February 2026–present: SPAR Fellow (Mentee)
  • Cornell University
  • Working on AI Safety and Eigenbench with Prof. Lionel Levine

Skills

• Machine Learning
  • Supervised learning, metric learning, feature selection
  • Retrieval evaluation and benchmarking
• Algorithms & Systems
  • Approximate nearest neighbor search
  • Vector search for filtered datasets
  • Data structures, algorithm design
• Programming
  • C, C++, Python, Kotlin, Rust, JavaScript
• Tools & Frameworks
  • PyTorch, TensorFlow, scikit-learn, AWS, SQL, Git