Worn keys, sharp code.

A Principal Engineer’s running notebook on software, cloud and AI: things I’ve actually built and broken, patterns that held up, and the occasional dead end I’ll leave in for honesty’s sake.

Start here About me

Latest writing

  • Part 3 of 3, AI Voiceover Studio: Four Layers Between You and a Surprise Bill. A sound waveform with its last third highlighted.
    Four Layers Between You and a Surprise Bill: The AWS Side of the Studio (Part 3 of 3)
    by Shailendra Karambe
    What one deploy command actually builds in your AWS account, who is allowed to press it, the four layers that stop a forgotten GPU from becoming a $600 bill, what the security scanners found, and everything the first real test run broke.
  • Part 2 of 3, AI Voiceover Studio: Inside the Studio. A sound waveform with its middle third highlighted.
    Inside the Studio: From a Video Description to Your Voice (Part 2 of 3)
    by Shailendra Karambe
    What actually happens between “describe your video” and a finished voiceover: a core that doesn’t care which model you use, a script written for the ear, one sentence at a time, two models sharing one GPU, and the UI I got wrong the first time.
  • Part 1 of 3, AI Voiceover Studio: Your Voice, Your Script. A sound waveform with its first third highlighted.
    Your Voice, Your Script: Building an AI Voiceover Studio You Actually Own (Part 1 of 3)
    by Shailendra Karambe
    Ten seconds of my voice, a description of the video, and a voiceover that sounds like me. How voice cloning actually works, why I didn’t just use an API, and how to run the whole thing in your own AWS account.
  • What Would It Take for You to Never Read Your Code Again?
    by Shailendra Karambe
    There have been so many perspectives on the future of AI and its effect on the human race, spanning the full spectrum from pessimism to optimism. However compelling the arguments behind any one of these perspectives are, one must not forget that they are, after all, just a perspective — formed in a limited context,…
  • Illustration: a man in silhouette at a control stick, steering a glowing wireframe jet across a dusk sky towards a city skyline.
    AI Myths – What a Principal Engineer Actually Sees Day to Day
    by Shailendra Karambe
    Generating code has become a commodity. That’s exactly why the software engineer’s role isn’t fading — it’s more important than ever. I wrote up the AI myths I keep running into as a Principal Engineer: why “AI belongs everywhere” is wrong, why commit counts are a broken way to measure productivity, and why prompt precision actually saves real money.

Find your way around