Swaroop Nath
Member of Technical Staff @ Reflection AI
Experience
Member of Technical Staff
Reflection AI
May 2026 – Present
Researcher
Google DeepMind
July 2024 – May 2026
AI/ML Research Intern
May 2023 – July 2023
Education
MS by Research, CSE
Indian Institute of Technology, Bombay
Aug 2021 – June 2024
About
Hi! I am a Member of Technical Staff at Reflection AI, working on enabling long-horizon reasoning and agentic capabilities.
Before this, I spent two years at Google DeepMind, in the Machine Learning and Optimization team led by Dr. Prateek Jain, where I worked on Efficiency — both in Pre-training and Post-training. My most significant work was on making Gemini's reasoning process efficient (more details in CV).
I graduated as an MS by Research scholar from the CFILT Lab, IIT Bombay. I was fortunate enough to be advised by Dr. Pushpak Bhattacharyya (God rest his soul) and Dr. Harshad Khadilkar. My Thesis was recognized with the Winifred B. Fernandes Research Excellence Award
. My works have been featured in A* NLP conferences — EMNLP and ACL.
Schedule a Conversation
I am happy to set aside 15 minutes for a conversation — on anything from feedback on an early idea to advice on your career, or a potential collaboration. If we have not met before, I would appreciate a brief introductory email ahead of the meeting.
News
-
October 2026
Reflection AI launched Beam, our open-weight frontier model: a 501B-parameter MoE (23B active) built for coding, reasoning and agentic tasks.
-
May 2026
Joined Reflection AI as a Member of Technical Staff, working on enabling long-horizon reasoning and agentic capabilities.
-
May 2026
Gemini 3.5 released, starting with 3.5 Flash.
-
February 2026
Gemini 3.1 Pro released, a step forward in core reasoning over Gemini 3 Pro.
-
November 2025
Gemini 3 released, Google’s most intelligent model family at launch.
-
March 2025
Gemini 2.5 released — Google’s first family of thinking models. Read the technical report, which I contributed to.
-
August 2024
Attending ACL 2024 in Thailand to present our paper:
One Prompt To Rule Them All: LLMs for Opinion Summary Evaluation
. -
June 2024
Received the
Winifred B. Fernandes Research Excellence Award
for my MS Thesis at IIT Bombay. -
June 2024
Graduated from IIT Bombay with an MS by Research in Computer Science & Engineering.
-
January 2024
Best talk award for
Efficient Reward Modelling in RLHF
at RISC'24, CSE@IIT-Bombay. -
December 2023
Attended EMNLP 2023 in Singapore to present our paper:
Reinforcement Replaces Supervision: Query focused Summarization using Deep Reinforcement Learning
. -
December 2023
Delivered a part of a tutorial on Vision-Language Models at ICON 2023.
-
August 2023
Delivered a tutorial on RLHF and Alignment Research at Qualcomm.
-
Dec 2022 & Jan 2023
Led IIT Bombay teams to Silver and Bronze Medals in Inter IIT Tech Meet.
Selected Publications (* = equal contribution)
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Google DeepMind (large-scale collaboration)
Technical Report · arXiv
Leveraging Domain Knowledge for Efficient Reward Modelling in RLHF
Swaroop Nath*, Tejpalsingh Siledar*, Pushpak Bhattacharyya, et al.
One Prompt To Rule Them All: LLMs for Opinion Summary Evaluation
Swaroop Nath*, Tejpalsingh Siledar*, Pushpak Bhattacharyya, et al.
Transformers are Expressive, But Are They Expressive Enough for Regression?
Swaroop Nath, Harshad Khadilkar, and Pushpak Bhattacharyya