Hi 👋! I'm Sid, a Research Engineer at Google Deepmind and a core contributor to Gemini. Previously, I was at Character AI working on LLM pretraining, where I picked hyperparameters for Noam Shazeer. I have deep expertise in training state-of-the-art LLMs.

When I'm not training models or performing research, you can catch me practicing the piano, playing table tennis or tweaking my Emacs config.

Experience
Filters:
💼 GDM Research Engineer
Google Deepmind
🗓️ Aug 2024 to Current
📍 Cambridge MA
💼 Research Engineer
Character.ai
🗓️ Dec 2023 to Aug 2024
📍 New York NY
🧐 Using RL and Synthetic Data to Teach Chatbots to Avoid Certain Topics
Suppressing Pink Elephants with Direct Principle Feedback
🗓️ Feb 2024
😃 Contributor
🌐 ACL
🔗 ArXiv
💼 Senior Machine Learning Engineer
Square
🗓️ Sep 2022 to Dec 2023
📍 Boston MA
🧐 Investigating Reasoning Capabilities of Large Language Models
OPT-R: Enhacing Reasoning Capabilities of Large Language Models
🗓️ May 2023
😃 Contributor
🌐 ACL Natural Language Reasoning and Structured Explanations workshop
🔗 ArXiv
🧐 Empirical investigation of masking strategies and rates in Vision-Language Pretraining
Uniform Masking Prevails in Vision-Language Pretraining
🗓️ Dec 2022
😃 First Author
🔗 ArXiv
🧐 Investigating Reasoning Capabilities of Large Language Models
ALERT: Adapting Language Models to Reasoning Tasks
🗓️ Oct 2022
😃 Contributor
🌐 ACL
🔗 ArXiv
💼 AI Resident
Meta (Facebook)
🗓️ Aug 2021 to Sep 2022
📍 Seattle WA
🧐 Reinforcement Learning based Chatbots using Large Language Models
CHAI: A Chatbot AI for Task-oriented Dialog with Offline Reinforcement Learning
🗓️ Apr 2022
😃 First Author
🌐 NAACL
🔗 ArXiv
🔗 Webpage
🔗 Code
💼 Machine Learning Intern
Apple
🗓️ Jun 2021 to Aug 2021
📍 Seattle WA
🧐 Reinforcement Learning based Chatbots using Large Language Models
CHAI: A Chatbot AI for Task-oriented Dialog with Offline Reinforcement Learning
🗓️ Jul 2021
😃 First Author
🌐 ICLR NeuCAIR workshop
🔗 ArXiv
🔗 Webpage
🔗 Code
💼 Undergraduate Researcher at Robotic AI and Learning Lab
Berkeley Artificial Intelligence Research Lab
🗓️ Jan 2019 to May 2021
📍 Berkeley CA
💼 Teaching Assistant, Deep Learning and Neural Networks
UC Berkeley EECS
🗓️ Jan 2021 to May 2021
📍 Berkeley CA
🎓 UC Berkeley
BA Computer Science & Music
🗓️ Aug 2017 to May 2021
📜 3.965
🧐 Reset-free robotic skill learning via Adversarial RL
Continual Learning of Control Primitives: Skill Discovery via Reset-Games
🗓️ Nov 2020
😃 CoFirst Author
🌐 NeurIPS
🔗 ArXiv
🔗 Code
🎓 The International School Bangalore
International Baccalaureate Diploma
🗓️ Aug 2015 to May 2017
📜 48.0