Home About Blog Resume

About Me

Hello,

I'm Aryamaan. I'm an Applied Scientist at Amazon and a graduate in Mathematics and Computing from IIT (ISM) Dhanbad. My work and research focus on Machine Learning, especially Efficient ML techniques like pruning, distillation, and quantization. I'm also deeply interested in Cryptography and Steganography.

Outside of work, I enjoy listening to Indian Hip Hop, watch tv-series and cooking.

Education

Integrated M. Tech. in Mathematics and Computing
Indian Institute of Technology (ISM), Dhanbad
2020 - 25 (Current CGPA - 8.65/10)

Highschool
The Tribhuvan School, Patna

Experiences

Applied Scientist, Amazon Lab126, Bangalore June, 2025 - Present
Efficient and sustainable deep learning
Research Intern, Nyun AI, Bangalore Aug, 2024 - Feb, 2025
Developed a small vision language model of 600M parameters
Research Intern, IBM Research Labs, Bangalore May, 2024 - Aug, 2024
Developed a time estimator for multi-GPU training of Large Language Models
Open Source Contributor, Google Summer of Code May, 2024 - Present
Evolutionary and Transformer Models for Symbolic Regression. Organization: ML4SCI
Global Alpha Researcher, Trexquant Aug, 2023 - Sep, 2023
Reviewed and implemented alpha trading strategies
Research Intern, Nyun AI May, 2023 - Aug, 2023
Developed a network compression method - Quantize aware Pruning using Distillation
Research Intern, Transmute AI Labs May, 2022 – Nov, 2022
Worked on making neural networks efficient by using Knowledge Distillation and making diffusion models faster by applying network slimming.
Research Intern, Real Maker Jul, 2022 – Aug, 2022
Worked on handling highly imbalanced class distribution problem.

Publications

Rethinking the Value of Training-Free Structured Pruning of LLMs
Nahush Lele, Arnav Chavan, Aryamaan Thakur, Deepak Gupta
Transactions on Machine Learning Research (TMLR), 2025