Kunal Jain

Kunal Jain

Systems researcher

Posts by Collection

portfolio

publications

A cloud-fog architecture for video analytics on large scale camera networks using semantic scene analysis

Published in 2023 IEEE/ACM 23rd International Symposium on Cluster, Cloud and Internet Computing (CCGrid), 2023

Distributed infrastructure for managing large scale camera networks.

Recommended citation: Kunal Jain, Kishan Sairam Adapa, Kunwar Grover, Ravi Kiran Sarvadevabhatla and Suresh Purini, "A Cloud-Fog Architecture for Video Analytics on Large Scale Camera Networks Using Semantic Scene Analysis," 2023 IEEE/ACM 23rd International Symposium on Cluster, Cloud and Internet Computing (CCGrid), Bangalore, India, 2023, pp. 513-523, doi: 10.1109/CCGrid57682.2023.00054.
Download Paper

Ensuring Fair LLM Serving Amid Diverse Applications

Published in Under Review, 2024

Fairness in serving multiple users and applications.

Recommended citation: Redwan Ibne Seraj Khan*, Kunal Jain*, Haiying Shen, Ankur Mallick, Anjaly Parayil, Anoop Kulkarni, Steve Kofsky, et al. ‘Ensuring Fair LLM Serving amid Diverse Applications’. arXiv [Cs.LG], 2024. https://doi.org/10.48550/ARXIV.2411.15997.
Download Paper

Seer: A Framework for Optimizing Traffic Camera Placement and Deep Learning Inference at the Edge for Vehicle Path Reconstruction

Published in 2024 IEEE/ACM Symposium on Edge Computing (SEC), 2024

Placement and deployment of edge cameras in cities.

Recommended citation: Siddhant Jain, Kunal Jain, Arun Ravindran and Suresh Purini, "Seer: A Framework for Optimizing Traffic Camera Placement and Deep Learning Inference at the Edge for Vehicle Path Reconstruction," 2024 IEEE/ACM Symposium on Edge Computing (SEC), Rome, Italy, 2024, pp. 333-345, doi: 10.1109/SEC62691.2024.00033.
Download Paper

Intelligent router for llm workloads: Improving performance through workload-aware scheduling

Published in The 5th Workshop on Machine Learning and Systems (EuroMLSys) co-located with EuroSys'25, 2025

Load balancing amid multiple instances of the same LLM

Recommended citation: Kunal Jain, Anjaly Parayil, Ankur Mallick, Esha Choukse, Xiaoting Qin, Jue Zhang, Íñigo Goiri, Rujia Wang, Chetan Bansal, Victor Rühle, Anoop Kulkarni, Steve Kofsky, Saravan Rajmohan, Microsoft . 2025. Performance Aware LLM Load Balancer for Mixed Workloads. In The 5th Workshop on Machine Learning and Systems (EuroMLSys ’25), March 30-April 3, 2025, Rotterdam, Netherlands. ACM, New York, NY, USA, 12 pages. https://doi. org/10.1145/3721146.3721947
Download Paper

talks

teaching

Teaching Assistant, Computer Programming

Undergraduate course, IIIT Hyderabad, 2022

Teaching Assistant for the Computer Programming undergraduate course, instructed by Prof. Suresh Purini. Responsible for preparing coding assigments and labs for 300 students and conducting tutorials and correcting papers for 30 students.

Teaching Assistant, Data Structures and Algorithms

Undergraduate course, IIIT Hyderabad, 2023

Teaching Assistant for the Data Structures and Algorithm undergraduate course, instructed by Prof. Ravi Kiran and Prof. Sujir Gujar. Responsible for preparing coding assigments and labs for 300 students and conducting tutorials and correcting papers for 30 students.

Teaching Assistant, Advanced Algorithms

Graduate course, IIIT Hyderabad, 2024

Teaching Assistant for the Advanced Algorithm graduate level course, instructed by Prof. Suryajit Chillara. Responsible for taking tutorials on Randomized Algorithms, Graph Algorithms, etc and paper correction for a class size of 50.