Hi, I’m Pavan 👋
Senior AI Engineer exploring the intersection of AI and systems programming using Mojo.
What You’ll Find Here
🧠 AI
- Quantization — Making models smaller and faster
- Pruning — Neural network compression
- Distributed Training — Scaling to multi-GPU/multi-node
- Training Deep Networks
- LLM Reasoning
🔥 Mojo & Systems
- SIMD — Vectorization and low-level optimization
- Benchmarks — Performance comparisons
This is my digital garden — a living collection of notes, experiments, and learnings.