RAG with LlamaIndex, Elasticsearch, Llama3
I built a retrieval pipeline with LlamaIndex, Elasticsearch, and Llama3 to test local deployment workflows.
Projects
Projects
I enjoy building tools and applications to explore ideas in machine learning. This page highlights the projects I've shipped — from practical LLM agents to experimental ML pipelines.
Each entry outlines what it is, why I built it, and what I learned, with links to the code or deeper dives. The common thread is applying AI research to real-world problems and reflecting on the results.
Projects
Filter by tooling, topic, or impact to jump straight to the work that resonates.
LoRA and DoRA Implementation
I implemented LoRA and DoRA from scratch in PyTorch to understand the methods end to end.
Large Language Models with MLX
I explored chat tooling on Apple Silicon using MLX to understand the runtime and packaging story.
No projects matched your filters. Try a different keyword or tag.
Build principles
- Design feedback loops into every deployment so models keep learning from production signals.
- Favor simple scaffolding with strong observability over complex stacks that hide failure modes.
- Ship concise documentation with each release to make handoffs and iterations painless.