About Me

I’m a systems-minded software engineer who enjoys building reliable, production-grade software—and understanding what happens when it doesn’t behave as expected. I work across the stack—backend, frontend, and infrastructure—often owning projects end-to-end, from design to deployment.

I love building projects, often breaking them, and learning from the failures and experiments that follow. This blog is a reflection of that process: what I tried, what went wrong, what worked, and what I’d do differently next time. Much of my work sits at the intersection of AI systems and engineering—deploying LLM and multimodal models, optimizing inference, and automating document-heavy workflows.

I care deeply about clean design, observability, and security in production. Writing code is only part of the job for me; I’m equally interested in how systems scale, fail, recover, and evolve over time.

Outside of coding, I run, swim, play badminton, and enjoy photography.