L
Leon Liu
SWE Intern @ TikTok • Prev MLE @ Jingo Jingo
📗 CS at UCLA building ML systems.
🏢 Shipped recommendation infrastructure at Jingo (AI startup) serving 5M products with RAG and vector search.
🔬 Diffusion models 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
Software Engineer Intern (Incoming)
Amazon (ATX Transformation) • Software Engineer Intern
AI Agents
LLM
Code Migration
AWS
Java
AWS
- Building AI agents to automate COBOL→Java migration of legacy government/banking systems
Software Engineer Intern
TikTok (Recommendation Infrastructure) • Software Engineer Intern
Recommendation Systems
Distributed Systems
Performance
Backend Engineering
C++
- Building recommendation ranking infrastructure in C++, modeling feature extraction and computation as parallel DAGs to maximize parallelism and reduce inference-time latency
- Optimizing inter-service communication and compute/cache placement to reduce latency and CPU usage
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
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
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
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
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
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
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
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
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
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
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
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
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