Rishab Vempati
I'm a Computer Science & Artificial Intelligence undergraduate at Purdue University. I research computer-use agents in the CIDER Lab with Prof. Jason Wu, specifically training vision-language models to navigate and evaluate user interfaces.
More broadly, I'm interested in machine learning beyond the agent setting: how models are trained and post-trained, reinforcement learning, and building the systems that make them work in practice. I'm always open to research collaborations and new problems in these areas.
News
- Aug 2026Joining IBM Watsonx Orchestrate as a Software Engineering Co-op.
- Feb 2026Started research in the CIDER Lab with Prof. Jason Wu; submitted uxCUA to UIST 2026.
Research
Agentic systems, Reinforcement Learning for VLMs, and Computer Vision
Computer-Use Agents for UI Usability
Feb 2026 – Aug 2026- Training a computer-use agent for automated UI usability assessment via RL-based fine-tuning of vision-language models.
- Running large-scale agent rollout generation and evaluation on NVIDIA H100 GPU clusters.
- Designing navigation quality heuristics and reward functions to improve agent exploration behavior.
Probabilistic Demand Forecasting
Jan 2024 – May 2024- Developed MLE and Bayesian inference algorithms to select optimal forecasting models across 10K+ product SKUs.
- Built outlier detection and clustering pipelines (Isolation Forest, GMMs), improving forecast accuracy by 3%.
Parking Lot Detection & Mapping
2024- Developed a U-Net segmentation model for satellite imagery in a 5-person team, achieving an 84% IoU accuracy.
- Built an automated pipeline ingesting 50GB+ of Bing Maps imagery and containerized the training workflow with Docker.
- Contributed 5,000+ validated parking-lot annotations to OpenStreetMap for open-source urban mapping.
Publications
- [1]
Training Computer Use Agents to Assess the Usability of Graphical User Interfaces
Alice Gao, Weixi Tong, Rishab Vempati, Katharina Reinecke, R. Benjamin Shapiro, Tianyi Zhang, Jason Wu.
Under review at ACM UIST 2026.
- [2]
Enhancing Ensemble Algorithm & Calibration Process for Demand Forecasting
Aman Kumar, Arhan Chaudhary, Kapil Naresh, Rishab Vempati, Sahil Desai, Shreya Gupta, Siddh Patani, Siddharth Sancheti, Zachary Kirkeby.
The Data Mine, Purdue University, 2024.
Experience
Engineering roles building production AI and distributed systems.
Software Engineering Co-op · IBM — Watsonx Orchestrate
Incoming co-op on IBM's enterprise AI-agent platform.
Software Engineer, Part-Time · Ekai
Built RAG + MCP retrieval systems for enterprise knowledge.
Software Engineering Intern · AssetMark
Migrated a legacy service to event-driven microservices on Azure.
Software Engineering Intern · Accelera Payments
Built a Kafka streaming pipeline for ISO 20022 payments.
Get In Touch
I'm open to connecting about research collaborations, graduate school, or interesting problems in agentic AI.
Say Hello