about.sh

whoami

Mahesh Sathiamoorthy

Co-founder/CEO at Bespoke Labs

Previously: Staff Software Engineer @ Google DeepMind

cat bio.txt

B.Tech from IIT Kharagpur -> MS/PhD from USC -> Google (Brain, DeepMind) -> Bespoke Labs

echo $CONTACT

mahesh at smahesh dot com

Mahesh Sathiamoorthy
work.log
Recent Work

cat current_focus.md

I started Bespoke Labs in 2024. We focus on RL environment curation and Data curation.

cat previous_work.md

Previously, I was a Tech Lead in Google DeepMind and worked on LLM-based recommender models. In 2021, very few people were thinking about applying the bitter lesson to recommender systems. I kickstarted a project to scale recommender models using LLMs, which resulted in several research publications (and one best paper award) and many impactful launches across recommender systems such as YouTube.

Bespoke Labs
publications.bib
Selected Publications

grep -r "author:Sathiamoorthy" ./papers/

  1. Etash Guha, Ryan Marten, Sedrick Keh, Negin Raoof, Georgios Smyrnis, .. Maheswaran Sathiamoorthy, Alex Dimakis, Ludwig Schmidt. "OpenThoughts: Data Recipes for Reasoning Models". arXiv. 2025
  2. Yashar Deldjoo, Zhankui He, Julian McAuley, Anton Korikov, Scott Sanner, Arnau Ramisa, Rene Vidal, Maheswaran Sathiamoorthy, Atoosa Kasrizadeh, Silvia Milano, Francesco Ricci. "Recommendation with generative models". arXiv. 2024
  3. Yashar Deldjoo, Zhankui He, Julian McAuley, Anton Korikov, Scott Sanner, Arnau Ramisa, Rene Vidal, Maheswaran Sathiamoorthy, Atoosa Kasirzadeh, Silvia Milano. "A review of modern recommender systems using generative models (gen-recsys)". Proceedings of the 30th ACM SIGKDD conference on Knowledge Discovery and Data Mining. 2024
  4. Shashank Rajput, Nikhil Mehta, Anima Singh, Raghunandan H. Keshavan, Trung Vu, Lukasz Heldt, Lichan Hong, Yi Tay, Vinh Q. Tran, Jonah Samost, Maciej Kula, Ed H. Chi, Maheswaran Sathiamoorthy. "Recommender Systems with Generative Retrieval". arxiv. NeurIPS 2023
  5. Jiaxi Tang, Yoel Drori, Daryl Chang, Maheswaran Sathiamoorthy, Justin Gilmer, Li Wei, Xinyang Yi, Lichan Hong, Ed H. Chi, "Improving Training Stability for Multitask Ranking Models in Recommender Systems". arxiv. KDD 2023, Best Paper Award in Data Science Track.
  6. Wang-Cheng Kang, Jianmo Ni, Nikhil Mehta, Maheswaran Sathiamoorthy, Lichan Hong, Ed Chi, Derek Zhiyuan Cheng. "Do LLMs Understand User Preferences? Evaluating LLMs On User Rating Prediction". arxiv. Workshop on Personalized Generative AI, CIKM 2023.
  7. Anima Singh, Trung Vu, Raghunandan Keshavan, Nikhil Mehta, Xinyang Yi, Lichan Hong, Lukasz Heldt, Li Wei, Ed Chi, Maheswaran Sathiamoorthy. "Better Generalization with Semantic IDs: A case study in Ranking for Recommendations". Preprint 2023
  8. Kiran Vodrahalli, Rakesh Shivanna, Maheswaran Sathiamoorthy, Sagar Jain, Ed H. Chi. "Algorithms for Efficiently Learning Low-Rank Neural Networks". 2022 (preprint)
  9. Hussein Hazimeh, Zhe Zhao, Aakanksha Chowdhery, Maheswaran Sathiamoorthy, Yihua Chen, Rahul Mazumder, Lichan Hong, Ed H Chi. "DSelect-k: Differentiable Selection in the Mixture of Experts with Applications to Multi-Task Learning". NeurIPS 2021 [arxiv]
  10. Zhe Zhao, Lichan Hong, Li Wei, Jilin Chen, Aniruddh Nath, Shawn Andrews, Aditee Kumthekar, Maheswaran Sathiamoorthy, Xinyang Yi, and Ed Chi. 2019. "Recommending what video to watch next: a multitask ranking system". In Proc. of the 13th ACM Conference on Recommender Systems (RecSys '19). ACM, New York, NY, USA, 43-51. DOI: https://doi.org/10.1145/3298689.3346997 [Google]
  11. Stephen Macke, Alex Beutel, Tim Kraska, Maheswaran Sathiamoorthy, Derek Zhiyuan Cheng, Ed H. Chi. Lifting the Curse of Multidimensional Data with Learned Existence Indexes. ML for Systems workshop at NeurIPS, 2018. [pdf]
  12. Maheswaran Sathiamoorthy, Megasthenis Asteris, Dimitris Papailiopoulos, Alex G. Dimakis, Ramkumar Vadali, Scott Chen, Dhruba Borthakur, "XORing Elephants: Novel Erasure Codes for Big Data", VLDB 2013.
talks.log
Recent Talks

ls -la ./talks/2025/

  1. OpenThoughts: Snowflake, 2025
  2. OpenThoughts: Uber India, 2025
  3. OpenThoughts: Infosys India, 2025
  4. OpenThoughts: Lossfunk, Bangalore, 2025
  5. Podcast: From Prompts to Policies: How RL Builds Better AI Agents, 2025