Work Experience
Research Assistant AI/XR - Spatial Interaction & Interaction Design Lab
May 2025 - Current - College Station, TX
- Developed VR anatomy navigation system in Unity(C#) for Meta Quest 3 with multimodal interaction (Voice + UI)
- Integrated Azure Speech-to-Text and Hugging Face models to deliver real-time, low-latency transcription in VR.
- Leveraged LLM APIs (Claude, Gemini) for semantic interpretation of anatomy-specific commands, improving accuracy with medical terminology
- Built a semantic parsing pipeline to extract actions (zoom/rotate/highlight) and anatomical targets, benchmarking sentence similarity models against LLM-based approaches.
- Engineered a modular logging framework to capture end-to-end latency and user study metrics.
- Designed logs to enable AI vs. Human-Assisted performance comparisons, supporting user study metrics.
Technical Product Manager - Develop for Good (AllGrow)
Oct 2024 - Feb 2025 - Remote
- Led 8 developers; shipped a React Native MVP for students & teachers.
- Ran weekly sprints and integrated stakeholder feedback into the roadmap.
- Designed a scalable architecture targeting 1M+ users.
Medical Device Product Development Intern - Alcon
May 2024 - Aug 2024 - Lake Forest, CA
- Developed a full-stack web application using Blazor, C# and .NET to streamline projects for medical devices.
- Enchanced ORA system software with intuitive C# and WPF interfaces, improving ease of use and accuracy.
- Applied ORA and AnalyzOR expertise to enhance documentation, development and application.
Undergraduate Research Student - UrbanResilience.AI Lab
May 2023 - May 2024 - College Station, TX
- Developed a python program to analyze lifestyle recovery impacts after Hurricane flood damage.
- Processed mobility data with Pandas, Numpy, Stats and GeoPandas to visualize vulnerable regions.
Software Engineer Inter - Uhnder Inc.
May 2022 - Aug 2022 - Austin, TX
- Built a Python program for BLR data analysis in ADAS Lidar, delivering six features to improve chip reliability
- Ensured 24x7 reliable operation by implementation features validated on 2+ years of historical data.
- Achieved 60% faster data analysis by modeling with linear regression per SPEC using Pandas and NumPy.