Etc.·

I'm Shikha — AI infrastructure engineer and writer. I work on the systems that make large language models run fast: inference optimization, GPU programming, quantization, and the parts where math meets metal.

Before the GPUs, I wrote stories. I still do. The two things aren't as separate as they sound — both are about finding the precise structure underneath something that looks like chaos.

I'm currently focused on AI inference engineering: understanding how transformers actually run on hardware, and building toward work at that intersection.