Atif Quamar

Atif Quamar

23, New Delhi

About Me

Currently working on making LLMs better reasoners at UC San Diego. Previously, at Purdue University, my research focused on inference-time alignment for language models. I founded Insituate, where we shipped agentic systems to global banks and financial institutions. I earned my bachelors in Computer Science and Biosciences from IIIT Delhi in 2024, and have a deep passion for AI, particularly in exploring and expanding the capabilities of language models.

My research explores methods to enhance language model reasoning, generalization, and alignment with human goals by building AI systems that are adversarially robust, decision-transparent, and computationally efficient. While LLMs are a primary area of interest, I’m also open to exploring other areas that have the potential to significantly expand the capabilities of intelligent systems.

I am currently looking for research opportunities in both academia (PhD) and industry for a 2026 start.

Interests
  • Large Language Models
  • Reasoning in LLMs
  • Reinforcement Learning
Education

  • B.Tech in Computer Science and Biosciences, 2020-2024

    IIIT - Delhi

Experience

 
 
 
 
 
University of California - San Diego
Research Intern
University of California - San Diego
Jul 2025 – Present San Diego, California, United States
Working on multimodal reasoning - interleaving text and visuals within the chain-of-thought, enabling models to “think” with sketches, diagrams, and images. This work bridges language and vision to solve complex problems with richer, more interpretable reasoning.
 
 
 
 
 
Purdue University
Research Assistant
Purdue University
Feb 2025 – Present West Lafayette, Indiana, United States
Proposed an inference-time alignment method that outperforms the SOTA - Best-of-N decoding by over 30%, while reducing reward model calls by 20%. Aligned LLMs in reducing harmlessness, improved reasoning and positive sentiment generation. Submitted the work to AAAI’26 conference and TACL journal.
 
 
 
 
 
Insituate
Founder & CTO
Insituate
Sep 2023 – Feb 2025 New Delhi, India
Founded and scaled an AI startup to $250K ARR. Shipped agentic solutions to global banks and financial insitutions.
 
 
 
 
 
Tweek Labs
Software Engineering Intern
Tweek Labs
May 2023 – Jul 2020 New Delhi, India
Engineered the company’s android’s application. Worked on Jetpack-Compose library for developing. Developed multiple features currently running in production.
 
 
 
 
 
Singapore University of Technology & Design
Research Intern
Singapore University of Technology & Design
Sep 2022 – Dec 2021 Singapore
Designed an edge-friendly Stream Processing Engine (SPE) with a congestion-aware scheduler, optimizing task-to-resource allocation using graph-based optimization.

Projects

Greedy, Not Needy - A General Paradigm for Efficient Decoding in Large Language Models
Adaptively focuses computation on the most critical early tokens during LLM decoding, boosting alignment performance across multiple tasks compared to Best-of-N and fine-tuning.
Greedy, Not Needy - A General Paradigm for Efficient Decoding in Large Language Models
STARS - Segment-level Token Alignment via Rejection Sampling in Large Language Models
Decoding method that aligns large language models with human preferences at inference time by accepting only high-reward text segments, boosting quality without retraining.
STARS - Segment-level Token Alignment via Rejection Sampling in Large Language Models

Contact