Story
I studied Electrical and Electronics Engineering and graduated in 2020, right in the middle of COVID.
For the first few months, I did what a lot of people did during lockdown — watched movies, web series, and mostly enjoyed having some unexpected free time.
After a while, though, I started thinking seriously about what I wanted to do next.
That was when I began learning programming on my own.
I tried different things, eventually found Flutter, and started building mobile apps. What began as curiosity slowly became something I wanted to pursue as a career.
By the time I got my first software job, I had already made the transition from electrical engineering to software.
I was a self-taught developer, and I wanted to keep going.
The work kept getting broader.
I started mostly with mobile apps, but the problems rarely stayed inside the app.
Over the years, I ended up working with backend services, document processing, OCR, realtime systems, web applications, native integrations, and cloud infrastructure.
I never really decided to become a “full-stack engineer.”
I just kept learning whatever the next problem required.
That became the way I worked: understand the problem, build something, find what I was missing, and learn that next.
AI started the same way.
I began exploring LLMs because I was curious about them.
I started with models and retrieval, then moved into tools, MCP, agents, and multi-agent systems.
Over time, I became less interested in whether an AI demo could work and more interested in what it takes to make one useful and dependable in the real world.
That's a large part of what I do today.
At Junglee Games, I work on AI Hub, an internal platform for building and using AI agents.
My work is mostly around the systems that make those agents useful — connecting them to tools and knowledge, supporting different models and workflows, enabling agents to work together, and making the platform reliable enough for everyday use.
Working on it has made one thing very clear to me:
The model is only one part of an AI product.
The rest is still software engineering — understanding the problem, connecting systems, handling failures, making trade-offs, and building something people can actually use.
Looking back
None of this was planned.
What started as learning programming during an unexpected break became a career I genuinely enjoy, and each step since has taken me somewhere I didn't expect.
I still don't know exactly where it leads next.
But I'm grateful I started — and forever grateful for the journey so far.