Rajan Agarwal

As a constrained optimization problem, LLMs can use RL to invent their own compression schemes to increase its context window.

Open-source background coding agent with 1.4k stars on GitHub. Feature-filled agent that works in a MicroVM with full codebase understanding.

In my internship with Amazon AGI, I worked on RL for a browser-use model. I led model performance on two public benchmarks & worked on algorithms.

Language models, when trained on hidden-information games, naturally learn deceptive techniques to win the game by any means.

Research under Cohere Labs for a compute-efficient post training to represent different languages as modalities for multilingual language models.

Giving vision to Karpathy's nanochat for <$10 of compute, by implementing LLaVA via SIGLIP encoder injection and fine-tuning on vision Q&A.

Multimodal agent and long-context video understanding to help hollywood editors. Worked on the the most powerful video retrieval and editing agent.

Tricked a Galaxy S24 to run Moondream 3B VLM locally, with quantization + local linux setup on phone. Built at TreeHacks 2025

Designed and implemented GPU-optimized voxel grids for humanoid design team in Waterloo. Co-led ML team.

A decentralized cross-device model training system with model and tensor parallelism to reduce compute needed to train large models.

One of the first implementations of coding subagents to work together to solve hard, diverse coding problems.

Long-term memory with multimodal knowledge graphs to search 7 days of video and audio within 5 seconds. Winners @ Hack the North 2023.

Deep learning analysis of seismic frequencies and local policy to design affordable earthquake-resistant buildings. Worked under RippleX Fellowship, RBCx.

An offline mesh network written in Swift via MultiPeer Connectivity to allow for cross-device transfer of files entirely offline, creating a chain of encrypted nodes.