Articles
Notes on production AI systems, RAG, and distributed inference—written for engineers and hiring managers who care about shipping.
Aug 7, 2026 · 2 min read
Notes on Distributed LLM Inference at Practical Scale
Engineering notes from my experience working with distributed LLM inference—trade-offs in partitioning, communication overhead, and when a distributed approach actually provides benefits compared to a single stronger node.
- LLM
- Distributed Systems
- Research
Aug 7, 2026 · 2 min read
Building RAG for Production Beyond Just a Demo
Practical lessons from building retrieval-augmented generation systems used by real users—from chunking and evaluation to latency budgets and failure modes that truly matter in production.
- AI
- RAG
- Engineering