I’m an AI engineer deeply interested in infrastructure and system design.

Most of my time goes into building and experimenting with things like LLM serving systems, AI agent orchestration, quantization, fine-tuning, generative AI tools, performance optimization, and scalable backend architectures. I like understanding how these pieces behave in real systems, not just in theory.

I’m curious about the intersection of AI systems, distributed systems, performance engineering, product scalability, and applied optimization theory. Building bias >> Tutorials and Reading. I try to reason from first principles and occasionally borrow ideas from game theory when thinking about incentives, trade-offs, and system dynamics.