Hello! I'm an Applied Scientist at Amazon, where I build and evaluate agentic AI systems. My current work focuses on user simulation: building agentic "twins" of users. I completed my PhD at Penn State University, advised by Prof. Dongwon Lee in the PIKE research group, and was a Visiting Scholar at New York University in Prof. He He's group. My PhD research focused on machine-generated text detection, authorship attribution, and obfuscation for Large Language Models (LLMs), and on what does or doesn't make LLM-generated text "human-like." Along the way, I was a research intern at Google, Samsung Research America, and Cadence Design Systems, building RL, NLP, and ML solutions for dialogue-based recommenders, voice assistants, and hardware design layouts. I'm broadly curious about cognitively plausible architectures for language applications, and always happy to connect.

News

Oct 2026 Presenting AgenTwin: An End-to-End Framework for Building Agentic Twins of Mobile Users at the COLM 2026 Workshop on Agent Behavior

Feb 2025 Joined Amazon as an Applied Scientist

Dec 2024 Completed my PhD at Penn State University

Earlier news

May 2024 Paper on paraphrased text authorship titled A Ship of Theseus: Curious Cases of Paraphrasing in LLM-Generated Texts accepted to ACL 2024

Apr 2024 Attended the Women in Cybersecurity Conference WiCyS in Nashville, TN

Mar 2024 Won the Graduate Student Award for Excellence in Teaching Support (College of IST, Penn State) 2023-2024 for the course "Socially Responsible Artificial Intelligence"

Mar 2024 Paper on using statistical psycholinguistic features to detect Deepfake Texts, GPT-who: An Information Density-based Machine-Generated Text Detector, accepted to NAACL Findings 2024

Feb 2024 Paper on authorship obfuscation using syntactic stylometry titled ALISON: Fast and Effective Stylometric Authorship Obfuscation at AAAI 2024

Nov 2023 New preprint titled A Ship of Theseus: Curious Cases of Paraphrasing in LLM-Generated Texts is available on arXiv

Oct 2023 Tutorial titled Catch Me If You GPT: Tutorial on Deepfake Texts accepted to NAACL 2024

May 2023 Paper on evaluation of decoding algorithms titled How do decoding algorithms distribute information in dialogue responses? at EACL Findings 2023

Experience

Applied Scientist, AmazonFeb 2025 - Present

Building and evaluating agentic AI systems, with a focus on user simulation.

Research Intern, Google (Google Assistant)May - Aug 2020

Built a recommender dialogue agent using hierarchical Soft Actor-Critic for a hybrid action space, learning user preferences through conversation and suggesting marketplace items. Ran ablations on agent design and simulated data using TF-Agents and Google Vizier.

Research Intern, Samsung Research AmericaMay - Aug 2018

Built an NLU intent-to-action service for Bixby using semantic similarity and word embeddings. Deployed it as a REST API and integrated it end-to-end with mobile devices.

Machine Learning Intern, Cadence Design SystemsMay - Aug 2017

Built ML pipelines for proprietary chip layout images and a hierarchical clustering prototype for assisted labeling, reaching 75% accuracy across four abstraction levels.

Research

Overview figure for AgenTwin
AgenTwin: An End-to-End Framework for Building Agentic Twins of Mobile Users Authors: Saranya Venkatraman, Thanh Tran, Shunyan Luo, Devin Chen, Yuning Wu, Kai Wei, Allie Colin, Guido Imbens, Ido Rosen, Christine Ambrose
COLM 2026 Workshop on Agent Behavior
[paper]
Overview figure for CollabStory
CollabStory: Multi-LLM Collaborative Story Generation and Authorship Analysis Authors: Saranya Venkatraman, Nafis Irtiza Tripto, Dongwon Lee
NAACL Findings 2025
[paper][code]
Overview figure for GPT-who
GPT-who: An Information Density-based Machine-Generated Text Detector Authors: Saranya Venkatraman, Adaku Uchendu, Dongwon Lee
NAACL Findings 2024
[paper][code]
Overview figure for A Ship of Theseus
A Ship of Theseus: Curious Cases of Paraphrasing in LLM-Generated Texts Authors: Nafis Irtiza Tripto, Saranya Venkatraman, Dominik Macko, Robert Moro, Ivan Srba, Adaku Uchendu, Thai Le, Dongwon Lee
ACL 2024
[paper]
Overview figure for ALISON
ALISON: Fast and Effective Stylometric Authorship Obfuscation Authors: Eric Xing, Saranya Venkatraman, Thai Le, Dongwon Lee
AAAI 2024
[paper][code]
Overview figure for ClassInSight (CHI 2024)
ClassInSight: Designing Conversation Support Tools to Visualize Classroom Discussion for Personalized Teacher Professional Development Authors: Tricia J Ngoon, S Sushil, Angela Stewart, Ung-Sang Lee, Saranya Venkatraman, Neil Thawani, Prasenjit Mitra, Sherice Clarke, John Zimmerman, Amy Ogan
CHI 2024
[paper]
Overview figure for decoding algorithms paper
How do decoding algorithms distribute information in dialogue responses? Authors: Saranya Venkatraman, He He, David Reitter
EACL Findings 2023
[paper][dataset]
Overview figure for The Sentiment Problem
The Sentiment Problem: A Critical Survey towards Deconstructing Sentiment Analysis Authors: Pranav Narayanan Venkit*, Mukund Srinath*, Sanjana Gautam, Saranya Venkatraman, Vipul Gupta, Rebecca J Passonneau, Shomir Wilson
EMNLP 2023 Outstanding Paper Award
[paper][data]
Overview figure for ClassInSight (EARLI 2021)
ClassInSight: Automating Analysis of Classroom Dialogue to Support Teacher Noticing and Reflection Authors: Saranya Venkatraman, Prasenjit Mitra, Sherice N. Clarke, Andrea Gomoll, Zaynab Gates, Sushil S, Tarang Tripathi, Amy Ogan
EARLI 2021
[paper][code]

Tutorials

Beyond Research

Support for students. As a first-generation student, I know college and graduate school bring challenges that aren't always visible to others, from financial concerns to simply feeling out of place. I've also navigated advisor transitions during my PhD; James McLaughlin's post "When your advisor leaves" is a useful starting point if you're in a similar situation. If you're facing any of these challenges, feel free to reach out by email. I'm happy to help.

Other interests. In my free time, I enjoy running, biking, snowboarding, and listening to and collecting vinyl records. In another life, I was a singer trained in Indian Classical Vocals and part of an a cappella group.

Running Biking Snowboarding Vinyl records

CV

You can download my CV here.