Hi, I'm Suhas.

Building thoughtful software with AI, product, and research.

SDE @a

Projects

Featured Projects

Click any project card to view full details.

AI COSMETIC ASSISTANT

Mirror

Mobile assistant that analyzes facial features and generates personalized skin and hair product recommendations.

ExpoGemini APIFlaskExpressMongoDB

FOOD REDISTRIBUTION PLATFORM

Meal Connect

Connects restaurants and shelters with geospatial matching and LLM summaries to speed up food redistribution.

Node.jsTypeScriptMongoDBExpressGoogle Maps API

RESEARCH ENGINEERING PROJECT

Foundry

Private research repo focused on scalable ML workflows and tooling for high-volume biomedical analysis.

PythonML PipelinesData Engineering

PERSONAL PRODUCTIVITY SYSTEM

Life Data Unifier

A local-first system that reconstructs a single truthful timeline of commitments across apps like Gmail and Calendar.

PythonFastAPILocal-firstData Pipeline

Research

Active Focus Areas

AI SafetyInterpretable AI

SafePro: Evaluating the Safety of Professional-Level AI Agents

Kaiwen Zhou, Shreedhar Jangam, Ashwin Nagarajan, Tejas Polu, Suhas Oruganti, Chengzhi Liu, Ching-Chen Kuo, Yuting Zheng, Sravana Narayanaraju, Xin Eric Wang

arXiv:2601.06663, 2026

PDF

BibTeX

@article{zhou2025safepro,
  title={SafePro: Evaluating the Safety of Professional-Level AI Agents},
  author={Zhou, Kaiwen and Jangam, Shreedhar and Nagarajan, Ashwin and Polu, Tejas and Oruganti, Suhas and Liu, Chengzhi and Kuo, Ching-Chen and Zheng, Yuting and Narayanaraju, Sravana and Wang, Xin Eric},
  journal={arXiv preprint arXiv:2505.16186},
  year={2026}
}

Mouse-Guided Gaze: Semi-Supervised Learning of Intention-Aware Representations for Reading Detection

Seongsil Heo, Roberto Manduchi

arXiv:2509.19574, 2025

PDF

About

I'm a software engineer based in the Bay Area.

I recently graduated in Computer Science from UC Santa Cruz and will be joining Amazon as a Software Development Engineer in July.

My background includes research in AI safety, interpretability, and multimodal learning, which shaped how I think about reliability and real-world deployment of intelligent systems.

I'm most energized by problems at the intersection of large-scale systems and machine learning: building software that scales while making sure the models behind it are robust and well-understood.

Outside of work, I build side projects, mentor students, and explore how emerging technologies can move from research into practical use.

Baskin Engineering

Group Tutor

Fall 2024 - Present

Amazon

Software Development Intern

June 2025 - Sept 2025

Let's connect!

I'm always excited to discuss engineering challenges, research opportunities, startup ideas, or AI technology.