I am a Software Engineer at Google DeepMind, where I work on training the Gemini family of models using reinforcement learning. Previously, at Google Cloud, I worked on reliability and performance for large-scale AI infrastructure, focusing on detecting and mitigating silent data corruption across CPUs, TPUs, GPUs, and NICs.

My research focuses on AI for systems and systems for AI. I completed my Ph.D. in Computer Science at the University of Illinois at Urbana-Champaign, advised by Prof. Ravishankar K. Iyer. My dissertation research focused on establishing a reinforcement learning framework for the control, management, and optimization of large-scale heterogeneous computer systems.

News [More Entries]

Aug 10, 2026 I joined the Antigravity team at Google DeepMind.
Jul 7, 2026 Our paper on using compiler based instruction-duplication techniques to detect defect driven silent data corruption in CPUs has been accepted at MICRO 59.
Aug 28, 2025 Our paper on silent data corruption from defective chips has been accepted at IEEE Design & Test.
Nov 20, 2021 I finished my PhD and will be joining the Platforms-Performance team in Google as a Software Engineer.
Oct 20, 2021 Our paper on characterizing latency variation in serverless FaaS has been accepted at WoSC 2021.

Selected Publications [Full List: Publications, Projects]

2026

ITHICA: Intra-Thread Instruction Checking Approach for Defect-Induced Silent Data Corruptions.
Ioanna Vavelidou, Subho S. Banerjee, Eric X. Liu, Mike Fuller, Subhasish Mitra, Caroline Trippel.
MICRO 59 (2026).
- arXiv
- Paper

2025

Silent Data Corruption by 10× Test Escapes Threatens Reliable Computing.
Subhasish Mitra, Subho Banerjee, Martin Dixon, Rama Govindaraju, Peter Hochschild, Eric Liu, Bharath Parthasarathy, and Parthasarathy Ranganathan.
IEEE Design & Test.
- DOI
- arXiv
- GR

2021

BayesPerf: Minimizing Performance Monitoring Errors Using Bayesian Statistics.
Subho S. Banerjee, Saurabh Jha, Zbigniew T. Kalbarczyk, and Ravishankar K. Iyer.
ASPLOS 2021.

2020

Live Forensics for HPC Systems: A Case Study on Distributed Storage Systems.
Saurabh Jha, Shengkun Cui, Subho S. Banerjee, Tianyin Xu, Jeremy Enos, Mike Showerman, Zbigniew T. Kalbarczyk, and Ravishankar K. Iyer.
Supercomputing 2020.
- Best Paper & Best Student Paper Finalist
FIRM: An Intelligent Fine-Grained Resource Management Framework for SLO-Oriented Microservices.
Haoran Qiu, Subho S. Banerjee, Saurabh Jha, Zbigniew T. Kalbarczyk, and Ravishankar K. Iyer.
OSDI 2020.
- DOI
- arXiv
- Code
- Data
- Paper
Inductive-bias-driven Reinforcement Learning for Efficient Schedules in Heterogeneous Clusters.
Subho S. Banerjee, Saurabh Jha, Zbigniew T. Kalbarczyk, and Ravishankar K. Iyer.
ICML 2020.
ML-driven Malware that Targets AV Safety.
Saurabh Jha, Shengkun Cui, Subho S. Banerjee, James Cyriac, Timothy Tsai, Zbigniew T. Kalbarczyk, and Ravishankar K. Iyer.
DSN 2020.

2019

ML-based Fault Injection for Autonomous Vehicles: A Case for Bayesian Fault Injection.
Saurabh Jha, Subho S. Banerjee, Timothy Tsai, Siva K. S. Hari, Michael B. Sullivan, Zbigniew T. Kalbarczyk, Stephen W. Keckler, and Ravishankar K. Iyer.
DSN 2019.
AcMC²: Accelerated Markov Chain Monte Carlo for Probabilistic Models.
Subho S. Banerjee, Zbigniew T. Kalbarczyk, and Ravishankar K. Iyer.
ASPLOS 2019.
CAUDIT: Continuous Auditing of SSH-Servers To Mitigate Brute-Force Attacks.
Phuong M. Cao, Yuming Wu, Subho S. Banerjee, Justin Azoff, Alex Withers, Zbigniew T. Kalbarczyk, and Ravishankar K. Iyer.
NSDI 2019.

Subho Sankar Banerjee