Hey, I'm Sanjana!

Thanks for checking out my website! I'm a CS and AI student @ MIT. I have previously interned at Nasdaq and conducted research at MIT's Media Lab, Oakland University, and the University of Michigan. I love building cool projects and using software as a mechanism to solve challenges. I'm drawn to the AI space and am especially interested in how intelligent systems can be used to accelerate our world.

Outside of software, I love creative writing, historical fiction/sci fi novels, long distance running, and all music by Taylor Swift.

Feel free to reach out to me to chat about any of the above and more!

Research Projects

Node Perturbation for Gradient-Free Fine-Tuning of Large Language Models I'm currently working as an AI researcher at the Brain and Cognitive Sciences Department at MIT, where I'm finetuning LLMs with mechanisms inspired by the brain! Typical fine-tuning techniques include supervised learning and reinforcement learning with human feedback (RLHF). These methods are effective but time intensive, especially with their reliance on gradient descent and back propagation. Not to mention that the reliance on gradient descent and back propagation is not ideal for the brain. My research explores how we can emulate the brain's own learning mechanisms to fine-tune LLMs. In particular, we are utilizing evolutionary algorithms (evolution strategies) to fine-tune LLMs. Evolution strategies are a type of evolutionary algorithm that is inspired by the brain's own learning mechanisms. The results are promising, as we demonstrate that evolution strategies can achieve similar performance to RL policies like GRPO, but with a fraction of the time and resources. Computationally Emulating the Evolution of Eyesight using Reinforcement Learning I worked as an AI/ML undergraduate researcher at the Media Lab (Camera Culture group). I expanded an existing reinforcement learning (RL) framework in Python, PyTorch, and MuJoCo by training agents across diverse environments (multi-eye perception, adversarial setups) to test robustness and adaptability in navigation tasks. I also discovered an emergent “dragonfly” prediction strategy, where agents anticipated goal locations before arrival, demonstrating RL’s ability to uncover novel optimization behaviors. I engineered a hybrid approach combining supervised models (CNNs, MLPs) with RL by passing distance-to-goal predictions as inputs, improving learning efficiency and enabling multisensory input modeling. I finally validated the approach through trajectory mapping and performance benchmarking, achieving competitive results with baseline RL while reducing training complexity