L
Leon Liu
AI Researcher & Developer • Prev MLE @ Jingo
📗 CS at UCLA building ML systems.
🏢 Shipped recommendation infrastructure at Jingo (AI startup) serving 5M products with RAG and vector search.
🔬 Diffusion models on GPU clusters for autonomous driving world modelling and AR Video generation at UCLA VAIL (Lab).
🌱 Side projects:
- 🐍 RL agents for Atari Surround
- ⌨️ Transformer EMG→QWERTY decoder for keyboardless typing from biosignals
- 📝 SaaS resume builder accessible editor → LaTeX/ATS-friendly PDF
- ... and more!
Experience
Machine Learning Engineer Intern
Jingo (AI-Native E-commerce Startup) • Machine Learning Engineer Intern
Machine Learning
Backend Engineering
LLM
Vector Search
FastAPI
Redis
PostgreSQL
SQLAlchemy
- Architected and built the core LLM-powered product search + recommendation service infra with FastAPI, Redis, and PostgreSQL (SQLAlchemy ORM), integrating RAG for user memory, vector search across a 5M+ product catalog
- Cut search initial p95 latency by ~50% by optimizing async orchestration with FastAPI workers and Redis caching, enabling real-time infinite scroll
- Productionized contextual rec engine combining graph-based user memory with context signals (geolocation, weather, Pinterest profile), plus an LLM-based query preprocessor that improved product recall and rec relevance in A/B tests
- Shipped web/deep research feature with look-aside cache using Perplexity Sonar API powering review/spec product comparisons across products while minimizing latency and amortizing API cost
- Designed an LLM-driven ETL pipeline that transformed messy product data into enriched embeddings and structured metadata, boosting product recall and recommendation relevance
No preview available
🚧 No full page available yet 🚧
Undergraduate Researcher
UCLA Vision And Autonomy Intelligence Lab (VAIL) • Undergraduate Researcher
Gen AI
Diffusion
Simulation
PyTorch
DeepSpeed
SLURM
- Engineered diffusion-based simulator-to-realistic scene generation models grounded in driving simulator physics
- Trained Flux and SD3 models across 8 L40S GPUs using PyTorch w/ DeepSpeed and SLURM, improving training throughput (2x batch sizes)
- Trained adapter layers for simulator-conditioned diffusion models to improve realism in driving scene generation
Check out the project at Dreamland.
🚧 No full page available yet 🚧
Software Engineer Intern
UCLA Bionics Lab • Software Engineer Intern
Machine Learning
Computer Vision
Healthcare
PyTorch
MediaPipe
- Trained LSTM achieving >90% accuracy for automating stroke rehabilitation assessments
- Developed data pipelines integrating MediaPipe-based 3D triangulation, doubling clinical data processing throughput
No preview available
🚧 No full page available yet 🚧
Projects
Prolio — Resume Versioning App
Full Stack
SaaS
CI/CD
LaTeX
Next.js
React
Flask
PostgreSQL
Redis
GCP
Docker
OAuth
- Designed and deployed a full-stack SaaS resume platform with modular editing, multiple versions, Gemini LLM-powered reviews, and PWA client (Next.js, React, Tailwind, shadcn)
- Engineered microservice backend (Flask, PostgreSQL, Redis, Celery, GCP) with async LaTeX/PDF compilation and secure OAuth authentication
- Productionized infra with Docker, GitHub Actions, and GCP Cloud Build, enabling CI/CD and scaling
No preview available
🚧 No full page available yet 🚧
emg2qwerty — sEMG-to-QWERTY AI Text Decoding
Machine Learning
Signal Processing
PyTorch
PyTorch Lightning
Transformers
Python
- Trained Transformer sequence-to-sequence models to decode wrist-worn EMG signals into typed QWERTY text, enabling hands-free typing from biosignals
- Outperformed Meta's published ConvNet baseline by ~10% lower character error rate through Transformer and RNN fine-tuning
- Developed full training pipeline with preprocessing (log spectrograms, augmentation), CTCLoss optimization, and benchmark evaluation across GRU, LSTM, and Transformer architectures
- Increased training throughput by 2.5x via spectrogram down-sampling (125Hz→50Hz) with negligible accuracy loss, enabling faster experimentation
No preview available
🚧 No full page available yet 🚧
Lingsim — AI-Powered Language Learning App
Full Stack
AI/ML
EdTech
Chat
Speech Recognition
TTS
Next.js
React
Firebase
TypeScript
GPT-4
Whisper
- Built multilingual AI tutoring full-stack app integrating speech recognition (Whisper) + GPT-4 dialogue + ElevenLabs TTS to enable real-time conversational practice
- Demonstrated sub-second (~500 ms) speech→text→response→speech loop across ~10 languages, showcasing feasibility of real-time interactive AI tutors
- Designed end-to-end system with Next.js, React, Firebase, and REST APIs to support secure authentication and optimized low-latency chat
No preview available
🚧 No full page available yet 🚧
Reliable Transport Layer (TCP over UDP)
Networking
Systems Programming
C
- Built a custom transport protocol in C providing reliable, ordered delivery on top of UDP by adding packet retransmission, acknowledgments, and error detection
- Validated correctness with stress tests simulating dropped/out-of-order packets, demonstrating consistent end-to-end data integrity
No preview available
🚧 No full page available yet 🚧
Basilisk — Multi-Agent Social Deduction Simulator
LLM
Multi-Agent Systems
Game AI
Python
LangChain
Pydantic
Gemini
Ollama
- Developed framework to simulate and manage social deduction games with both human players and LLM-based agents
- Integrated LangChain and Ollama/Gemini APIs for multi-agent orchestration, dialogue, and strategy execution
- Implemented structured input/response validation with Pydantic, ensuring reliable agent interactions and reproducibility
- Built orchestration layer for game-state tracking, rule enforcement, and cross-agent coordination in Python
No preview available
🚧 No full page available yet 🚧
Finduo — Full-Stack Gaming Social Media Web App
Full Stack
Social Media
Gaming
MongoDB
Express
React
Node.js
TypeScript
- Designed and implemented full-stack social media platform for users to find gaming partners
- Implemented user profiles, dynamic feed, search capabilities, and viewing friend invites with React
- Implemented RESTful API for auth, user profiles, ratings, and friends list in the backend with MongoDB, Express, Node.js
No preview available
🚧 No full page available yet 🚧
Dynamic Analysis of Cryptographic API Misuse in Node.js
Security
Dynamic Analysis
Research
Node.js
TypeScript
Bash
- Paper accepted at IEEE MIT URTC
- Implemented multipart system to perform dynamic analysis on Node.js codebases to detect vulnerabilities from API misuse
- Implemented custom module loader that instrumented code to log API usage
- Developed rule enforcer to detect API misuse defined by a modular set of declarative rules
No preview available
🚧 No full page available yet 🚧
Unity Real-Time Strategy PVP Game
Game Development
Real-time Systems
C#
Unity
- Engineered robust game systems and mechanics, leveraging data structures to optimize performance
- Architected and implemented modular scripts and game systems with Object-Oriented Programming
- Utilized Unity Profiler for game performance tuning and software testing
- Enhanced user experience by identifying and resolving performance bottlenecks
No preview available
🚧 No full page available yet 🚧
Brewin Interpreter
Programming Languages
Interpreters
Compilers
Python
- Implemented an interpreter in Python for a custom language "Brewin"
- Designed interpreter for several variations of the language with common features
- Handled function calls, recursion, scoping, variables, control flow (conditionals and loops)
- Built systems for dynamic and statically-typed variations, structs, error handling, lazy evaluation
No preview available
🚧 No full page available yet 🚧
Reverse Proxy for ACM Cyber
Networking
Backend
Security
TypeScript
Deno
- Implemented a reverse proxy with HTTP request parsing, authentication (bcrypt), and structured logging to securely route and monitor backend traffic
- Designed and tested routing, auth, and logging subsystems to improve reliability and observability in multi-service environments
No preview available
🚧 No full page available yet 🚧
Atari Reinforcement Learning
Reinforcement Learning
Python
PyTorch
PyTorch Lightning
- Implemented policy gradient methods and deep Q learning for a reinforcement learning agent in Atari
- Trained agent to solve and beat the Atari Surround environment
- Spearheaded and taught a quarter-long workshop for ACM AI for 60+ members
No preview available
🚧 No full page available yet 🚧