Skip to content
Satyajit Sarangi

Now writing: inference engines & tool-call parsing

From tokens to kernels.
Notes on AI inference infrastructure.

I'm Satyajit, a systems engineer. I write long-form deep dives with code, math and benchmarks on how inference stacks actually work.

Focus areas

  • Inference engines
  • Tool-call parsing
  • LoRA serving
  • Constrained decoding
  • Compilers & IR
  • Benchmarks

// Recent Posts

All Posts