MS Human-Computer Interaction (CMU) | BS Computer Engineering + CS minor (UTSA)
Engineer across software, hardware, AI and XR. Experience in ML/CV, XR prototyping, mobile, and full-stack systems. Fast learner and strong builder. I like projects where I can connect multiple disciplines, ship something real, and keep learning.
Especially when it means turning messy problems into usable tools
- Applied ML / CV / Video pipelines (OpenCV, FFmpeg, Ray, Databricks, PySpark, MLflow, AWS S3)
- XR prototyping in Unity (C#) with a human-centered focus (perception, interaction, accessibility)
- AI product systems (LLM-backed tools that are grounded in real app context)
- Assuage (iOS): Sensing → ML distress prediction
HealthKit biometrics → real-time distress prediction with on-device inference (Swift/Core ML patterns) - Magic Mitts: affordable haptic VR glove (Capstone)
Flex sensing, Hand Tracking + electromagnetic braking + Unity integration (1st place UTSA Tech Symposium) - PlayStation: Gameplay video context extraction (internship)
Scalable video pipeline using S3, Ray, FFmpeg, OpenCV/OCR, Databricks/PySpark, MLflow - Magic Mitts: affordable haptic VR glove (Capstone)
Flex sensing + electromagnetic braking + Unity integration (1st place UTSA Tech Symposium) - VR Music Visualizer (Unity / Quest 2)
Interactive music-reactive VR visuals with planned hand-tracking interactions - Computer Vision projects
YOLOv5 vehicle detection + CNN-based image classification work (NACME) - Talky Talky (Google SPS)
Audio-responsive web app to support non-verbal kids using Text-to-Speech APIs
| Area | Tools |
|---|---|
| Languages | Python • C++ • C • Swift • Java • TypeScript/JavaScript • SQL |
| ML / CV | PyTorch • TensorFlow • scikit-learn • OpenCV • NumPy • pandas • EDA • model evaluation |
| Video / Data | FFmpeg • Ray • Databricks • PySpark • MLflow • AWS S3 • Snowflake |
| XR / 3D | Unity (C#) • Meta XR SDK • VR prototyping |
| Mobile | iOS (HealthKit, Core ML) • Android (Firebase, SQLite) |
| Build / Collab | Git/GitHub • Docker • CI/CD • Jira • Confluence • Jupyter |
Also used
- Deep Learning: CNNs, transfer learning, autoencoders, RNNs, embeddings
- Classical ML: clustering (k-means), PCA, SVM, decision trees, fairness/responsible AI
- Hardware / Embedded: Arduino, Raspberry Pi, ESP32, sensors, Verilog, PSpice, MATLAB
- Applied ML Intern (PlayStation) — video pipeline + scalable processing (S3, Ray, FFmpeg, OpenCV, Databricks)
- Apple NACME AI/ML Intensive (USC) — 35 hands-on ML projects across CV, NLP, clustering, deep learning
- Google SPS (2022) — built “Talky Talky” (audio-responsive web app for non-verbal kids)
😄 Pronouns: she/her
⚡ Fun fact: I love sci-fi + psychological movies, XR, and sleep (in that order 😄...backwards)