I am an applied ML and software engineering researcher at Meta, working on developing AI-based solutions to industry-scale software engineering problems. My research aims to address practical problems in software development, such as code generation/synthesis, code review, bug attribution, root cause analysis, etc. using machine learning solutions. The projects I have worked on have found significant industrial impact at Meta.
Publications
- Moving Faster and Reducing Risk: Using LLMs in Release Deployment
Rui Abreu, Vijayaraghavan Murali, Peter C Rigby, Chandra Maddila, Weiyan Sun, Jun Ge, Kaavya Chinniah, Audris Mockus, Megh Mehta, Nachiappan Nagappan
(arxiv) - AI-Assisted SQL Authoring at Industry Scale
Chandra Maddila, Negar Ghorbani, Kosay Jabre, Vijayaraghavan Murali, Edwin Kim, Parth Thakkar, Nikolay Pavlovich Laptev, Olivia Harman, Diana Hsu, Rui Abreu, Peter C. Rigby
(arxiv) - Multi-line AI-assisted Code Authoring
Omer Dunay, Daniel Cheng, Adam Tait, Parth Thakkar, Peter C. Rigby, Andy Chiu, Imad Ahmad, Arun Ganesan, Chandra Maddila, Vijayaraghavan Murali, Ali Tayyebi, Nachiappan Nagappan
FSE 2024 Industry Track (arxiv) - AI-assisted Code Authoring at Scale: Fine-tuning, deploying, and mixed methods evaluation
Vijayaraghavan Murali, Chandra Maddila, Imad Ahmad, Michael Bolin, Daniel Cheng, Negar Ghorbani, Renuka Fernandez, Nachiappan Nagappan, Peter C. Rigby
FSE 2024 (arxiv) - Highlight by Meta CEO Mark Zuckerberg FB/IG - Learning to Learn to Predict Performance Regressions in Production at Meta
Moritz Beller, Hongyu Li, Vivek Nair, Vijayaraghavan Murali, Imad Ahmad, Jürgen Cito, Drew Carlson, Gareth Ari Aye, Wes Dyer
AST 2023 - Detecting Privacy-Sensitive Code Changes with Language Modeling
Gokalp Demirci, Vijayaraghavan Murali, Imad Ahmad, Rajeev Rao, Gareth Ari Aye
MSR 2022 Industry Track - Counterfactual Explanations for Models of Code
Jurgen Cito, Isil Dillig, Vijayaraghavan Murali, Satish Chandra
ICSE SEIP 2022 - Improving Code Autocompletion with Transfer Learning
Wen Zhou, Sonia Kim, Vijayaraghavan Murali, Ari Aye
ICSE SEIP 2022 - Explaining mispredictions of machine learning models using rule induction
Jurgen Cito, Isil Dillig, Sonia Kim, Vijayaraghavan Murali, Satish Chandra
FSE 2021 - Industry-scale IR-based Bug Localization: A Perspective from Facebook
Vijayaraghavan Murali, Lee Gross, Rebecca Qian, Satish Chandra
ICSE SEIP 2021 - Distinguished Paper award - Scalable Statistical Root Cause Analysis on App Telemetry
Vijayaraghavan Murali, Edward Yao, Umang Mathur, Satish Chandra
ICSE SEIP 2021 - Scaffle: bug localization on millions of files
Michael Pradel, Vijayaraghavan Murali, Rebecca Qian, Mateusz Machalica, Erik Meijer, Satish Chandra
ISSTA 2020 - Debugging crashes using continuous contrast set mining
Rebecca Qian, Yang Yu, Wonhee Park, Vijayaraghavan Murali, Stephen Fink, Satish Chandra
ICSE SEIP 2020 - Neural query expansion for code search
Jason Liu, Sonia Kim, Vijayaraghavan Murali, Swarat Chaudhuri, Satish Chandra
MAPL 2019 - Programmatically Interpretable Reinforcement Learning
Abhinav Verma, Vijayaraghavan Murali, Rishabh Singh, Pushmeet Kohli, Swarat Chaudhuri
ICML 2018 - Neural Sketch Learning for Conditional Program Generation
Vijayaraghavan Murali, Letao Qi, Swarat Chaudhuri, Chris Jermaine
ICLR 2018 - Abridging Source Code
Binhang Yuan, Vijayaraghavan Murali, Chris Jermaine
OOPSLA 2017 - Bayesian Specification Learning for Finding API Usage Errors
Vijayaraghavan Murali, Swarat Chaudhuri, Chris Jermaine
FSE 2017 - A Path-Sensitively Sliced Control Flow Graph
Joxan Jaffar, Vijayaraghavan Murali
FSE 2014 - Lazy Symbolic Execution for Enhanced Learning
Duc-Hiep Chu, Joxan Jaffar, Vijayaraghavan Murali
RV 2014 - A Hybrid Algorithm for Error Trace Explanation
Vijayaraghavan Murali, Nishant Sinha, Emina Torlak, Satish Chandra
VSTTE 2014 - Boosting Concolic Testing via Interpolation
Joxan Jaffar, Vijayaraghavan Murali, Jorge A. Navas
FSE 2013 - Path-Sensitive Backward Slicing
Joxan Jaffar, Vijayaraghavan Murali, Jorge A. Navas, Andrew E. Santosa
SAS 2012 - TRACER: A Symbolic Execution Tool for Verification
Joxan Jaffar, Vijayaraghavan Murali, Jorge A. Navas, Andrew E. Santosa
CAV 2012 - Towards predictive modeling of message passing communication
Verdi March, Vijayaraghavan Murali, Yong Meng Teo, Simon See, James T. Himer
HPCC 2009
Blog Posts
- Minesweeper automates root cause analysis as a first-line defense against bugs
- CCSM: Scalable statistical anomaly detection to resolve app crashes faster
Service
- PLDI 2022
- ISSTA 2020
- CAV 2019
- POPL 2015 (Artifact Committee)
- FSE 2014 (Artifact Committee)
Bio
I have been a software engineer at Meta (Facebook) since 2018, where I work in developer infrastructure. Before, I was a Research Scientist (postdoc) at Rice University from 2015-2018, working with Swarat Chaudhuri and Chris Jermaine on the Pliny project. Prior to that, I was a Ph.D. student at the National University of Singapore (NUS) from 2009-2014, advised by Joxan Jaffar. I interned at IBM Research India during my Ph.D., working with Satish Chandra. My Ph.D. background is originally in programming languages and formal methods, and I became familiar with machine learning during my postdoc at Rice. I obtained my B.Computing also from NUS in 2009.
My hometown is Chennai in south India. Outside research, I enjoy video games, backyard gardening, and traveling.