I build machine learning systems that have to survive contact with production.
I'm a senior at the University of Mississippi studying Computer Science with a Data Science emphasis and a Math minor, graduating May 2027. Originally from Mongolia 🇲🇳, currently in Seoul as a Machine Learning Engineering Intern at PotatoNet, where most of my work sits between graph databases, deep learning, and the deployment plumbing that makes either one useful.
My longer-term interest is embodied AI and robot learning, which is to say the version of this problem where the model has to act, not just predict. Everything I build keeps circling the same question, which is what breaks when a model leaves the notebook.
Also a Break Through Tech AI Studio Fellow (selected from 4,000+ applicants nationwide) and a Teaching Assistant for 200+ students in Data Structures and Algorithms.
Note
🤖 Language-conditioned robot manipulation for my senior capstone, built on Hugging Face's LeRobot. Aiming at a workshop submission.
🔗 Graph-based threat intelligence @ PotatoNet, scaling attacker-family clustering across a live Neo4j store.
📚 Learning: Cypher and graph algorithms, vision-language-action models, and Rust for the parts of the stack Python shouldn't own.
Turning raw malicious JavaScript into named attacker "families" so analysts can chase infrastructure instead of individual scripts.
- Shipped a production graph-ETL pipeline backfilling six months of threat data into a live Neo4j store through idempotent, rollback-tagged loads, automated as a nightly self-healing cron job
- Built a 7-signal attacker-profiling engine clustering malicious JS via SimHash AST similarity, perceptual screenshot hashing, and shared TLS cert / IP / ASN / registrant infrastructure, using GDS Leiden community detection
- Diagnosed and fixed a 52K-script over-merge caused by benign library bridges between unrelated families, cutting max family size to 476 across 334 clean clusters
- Extracted a CNN-LSTM-Attention fault predictor (94.7% accuracy) out of a legacy Django monolith into a clean FastAPI service on a 16-container microservices platform, with zero-downtime deploys
Python · Neo4j / Cypher · PyTorch · FastAPI · Docker · Nginx · Gunicorn
Proprietary work. Happy to walk through the architecture and the debugging story.
| Project | What It Does | Tech |
|---|---|---|
| Census Income Classification 📌 | End-to-end ML pipeline on 32K+ census records. Tuned on F1 rather than accuracy to handle class imbalance, found a 3-layer Keras net barely beat logistic regression (0.70 vs 0.68), and shipped the simpler model. Audited coefficients for fairness, surfaced a discrimination risk, and recommended against lending deployment. | Python Scikit-learn Keras Pandas |
| Streaming Evaluation Protocol for CSLR 🔬 | A standardized evaluation protocol for streaming sign language recognition, adapting latency and stability metrics from streaming ASR and simultaneous MT to fill a gap left by offline-only benchmarks. Includes a fault-tolerant landmark extraction pipeline over PHOENIX-2014T. | Python MediaPipe Multiprocessing |
| Real-Time ASL Translation 🤟 | Live ASL recognition from webcam input, built for interactive frame rates on consumer hardware rather than batch inference. | Python TensorFlow OpenCV MediaPipe |
| CS2 Esports Statistics Tracker 📊 | Normalized relational schema for pro Counter-Strike teams, players, tournaments, and match performance, designed around the queries analysts actually run. | SQL Database Design |
Also on my profile: an e-commerce storefront in TypeScript/React and a desktop note-taking app in Python.
💻 Languages
🧠 ML & Computer Vision
☁️ Infrastructure & Data
🎓 Break Through Tech AI Studio Fellow · selected from 4,000+ applicants nationwide for a one-year applied ML fellowship
📜 Machine Learning Foundations e-Certificate · Cornell University via Break Through Tech
📜 Career Essentials in Generative AI · Microsoft & LinkedIn
💰 Freeman Grant Recipient · $9,000
⭐ Chancellor's Honor Roll · Fall 2024, Spring 2025 · GPA 3.78
👨🏫 Teaching Assistant & CS Tutor for 200+ students across four courses, plus 50+ one-on-one mentees. Teaching is the fastest way I've found to locate the holes in my own understanding.
🎾 Tennis · 🏋️ In the gym most mornings · 📈 Markets and valuation modeling as a hobby · 🇰🇷 Learning Seoul one subway line at a time
Open to conversations about embodied AI, robot learning, and anything that puts a model on real hardware.