Siddharth (Sid) Jha

I am a fourth-year undergraduate studying Electrical Engineering and Computer Science at UC Berkeley.

I am interested in efficient AI and data-oriented systems. Currently I work in Matei Zaharia's group in Sky Lab and Kurt Keutzer's group in BAIR. At Berkeley, I've been a head teaching assistant for Databases and a teaching assistant for Computer Architecture. I've also interned at NVIDIA, Databricks, YugabyteDB, and Pure Storage.

Email  /  Github  /  Twitter

profile photo
Main Work
Efficient and Scalable Estimation of Tool Representations in Vector Space
Suhong Moon*, Siddharth Jha*, Lutfi Erdogan, Sehoon Kim, Woosang Lim, Kurt Keutzer, Amir Gholami
arXiv, 2024
Characterizing Prompt Compression Methods for Long Context Inference
Siddharth Jha, Lutfi Erdogan, Sehoon Kim, Kurt Keutzer, Amir Gholami
Es-FoMo @ ICML (Oral), 2024
Learned Best-Effort LLM Serving
Siddharth Jha, Coleman Hooper, Xiaoxuan Liu, Sehoon Kim, Kurt Keutzer
Es-FoMo @ ICML, 2024
TinyAgent: Function Calling at the Edge
Lutfi Erdogan*, Nicholas Lee*, Siddharth Jha*, Sehoon Kim, Ryan Tabrizi, Suhong Moon, Coleman Hooper, Gopala Anumanchipalli, Kurt Keutzer, Amir Gholami
EMNLP Demo, 2024
Additional Work
Text2SQL is Not Enough: Unifying AI and Databases with TAG
Asim Biswal*, Liana Patel*, Siddharth Jha, Amog Kamsetty, Shu Liu, Joseph Gonzalez, Carlos Guestrin, Matei Zaharia
CIDR, 2025
LOTUS: Enabling Semantic Queries with LLMs Over Tables of Unstructured and Structured Data
Liana Patel, Siddharth Jha, Carlos Guestrin, Matei Zaharia
arXiv, 2024
An Evaluation of Memory Optimization Methods for Training Neural Networks
Xiaoxuan Liu, Siddharth Jha, Alvin Cheung
arXiv, 2023
Leveraging Application Data Constraints to Optimize Database-Backed Web Applications
Xiaoxuan Liu, Shuxian Wang, Mengzhu Sun, Sicheng Pan, Ge Li, Siddharth Jha, Cong Yan, Junwen Yang, Shan Lu, Alvin Cheung
VLDB, 2023

Website template from Jon Barron.