I am a fourth year PhD student in Electrical and Computer Engineering, Carnegie Mellon University advised by Prof. Gauri Joshi. I also collaborate with Prof. Guannan Qu.
At CMU, I design theoretically grounded algorithms for efficient ML Inference Systems. I have developed policy gradient based RL algorithms for efficient resource allocation in non-stationary and heterogeneous ML systems. My research interests broadly lie in reinforcement/machine learning, optimization and applied statistics.
I spent Summer '25 at Amazon in Santa Clara working on RL based adaptive RAG methods for LLM Agents.
I was previously a Software Engineer at Google working on optimizing Android for the Next Billion Users.
I pursued my undergraduate studies at IIT Bombay majoring in Electrical Engineering with a minor in Computer Science. I worked with Prof. Nikhil Karamchandani and Prof. Sharayu Moharir for my master's thesis. I also spent a semester abroad at D-ITET, ETH Zurich.
Proximity Weighted Non-Parametric LLM Query Routing
Shivam Patel, Neharika Jali, Ankur Mallick, Gauri Joshi
In Submission
Neharika Jali, Eshika Pathak, Pranay Sharma, Guannan Qu, Gauri Joshi
In Submission
Neharika Jali, Guannan Qu, Weina Wang, Gauri Joshi
International Conference on Artificial Intelligence and Statistics (AISTATS), 2024
Divyansh Jhunjhunwala*, Neharika Jali*, Gauri Joshi, Shiqiang Wang
IEEE International Symposium on Information Theory (ISIT), 2024
Neharika Jali, Nikhil Karamchandani, Sharayu Moharir
IEEE Transactions on Signal and Information Processing over Networks, 2022
IEEE International Symposium on Information Theory (ISIT), 2021 - Short version
* denotes equal contribution
A form designed to facilitate checking in with your advisor, often used by CMU SCS/ECE PhD students
Some advice on navigating a PhD by Prof. Aditya Ramdas
Applying to grad school in CS/ECE by Prof. Mor Harchol-Balter