AI Research Engineer in training, focused on LLMs, efficient local inference, and applied machine learning.
I enjoy turning research ideas into practical systems—and breaking systems safely through security research.
- Building and evaluating local LLM inference pipelines on Apple Silicon.
- Exploring model compression, quantization, KV-cache optimization, and efficient inference.
- Developing AI-powered tools with Python and modern ML/LLM workflows.
- Applying security research to smart contracts, bug bounties, and CTF challenges.
- AI Research Engineering: transformers, fine-tuning, evaluation, and inference optimization.
- Model compression: quantization, pruning, knowledge distillation, and efficient architectures.
- LLM systems: local inference, retrieval-augmented generation, benchmarking, and profiling.
- Blockchain security: smart-contract auditing, vulnerability research, and exploit development.
Python · PyTorch · LLMs · Machine Learning · Model Quantization
Efficient Inference · RAG · Apple Silicon / MLX · Security Research
Smart Contracts · Bug Bounty · CTFs
I aim to build reliable, efficient, and secure AI systems—especially models and tools that can run locally without sacrificing usability.
- Portfolio: waterway.github.io
- GitHub: @waterway
In my free time, I participate in bug bounties, smart-contract security research, and CTFs.
