Vova Zakharov · Developer – AI, full-stack, and the bits in-between
Developer with a physics-and-math brain and a knack for building practical tools that turn AI buzz into actual features. Ever since 2020, most of my work revolves around LLMs and image generation, following years of messing with smaller neural networks. This means I don't buy or sell buzzwords, I understand things a level or two deeper than most, and I've developed an intuition for what models can and cannot do.
I've built systems from scratch, simplified convoluted integrations, and turned vague ideas into working prototypes — across open-source, startups, and global advertising giants.
I work independently: a clear overall direction is enough, and I work out and finish the details myself. I own the result as if the product were mine, and I look past the code — if a task doesn't fit the product, I say so before building it.
My focus is TypeScript and applied LLM systems: I prototype them, take them to production, debug them, and stress-test AI initiatives.
I tend to stick to a more "economical" paradigm of AI usage: smaller prompts, a close eye on context limits, and no hoping that a model fed everything will sort it out on its own. My expertise predates the ChatGPT hype cycle, which means I understand not just the APIs, but the patterns and limitations underneath them — which is where most of the hard problems live.