Shaurya Singh

Seattle ↔ New Delhi

I find what hurts, then build at it.

That’s taken me to oceans, brains, street crime, protein structure, and AI agents — so far. The fields don’t repeat. The reason does.

Right now: undergraduate studies at UW, real-time voice and communications engineering, and merged fixes to model evaluation and grading tools.

engineering record all work résumé

33 fix pull requests and 238 issues, from the public GitHub record 238 issues filed in 229 repositories, 28 of them closed by maintainer-merged pull requests (the amber core). 33 fix pull requests around the ring: 3 merged, 1 revised fix merged, 1 shipped in release, 1 approved, 25 open, 2 closed; 24 with tests. Marks are sized by the target repository's GitHub stars.

The public record · as of 2026-11-02

issues filed
238
closed by maintainer-merged PRs
28
fix PRs opened
33
  • merged 3 revised fix merged 1 shipped in release 1
  • approved 1
  • open 25
  • closed 2
  • with tests 24
  • one dot per issue; amber, closed by a merged PR

Every pull request, plotted

I don’t take small problems. Oceans, brains, street crime, access, agents — every one of them was bigger than me when I started. That’s the filter, not an accident.

And I don’t walk in without an edge. If I don’t have one, I go build the thing that gives me one: the eval battery that attacks my own work, the model panel that judges my own words, the tool that reads the code before I do.

  1. problem Something that actually hurts someone — a traveler getting robbed, a kid locked out of CS, a paralysed brain, an acidifying ocean.
  2. prototype The most ambitious thing I can build at it with what I have. Ships rough before it ships polished.
  3. teach / give away The point was never to own it. Teach it, open it, or let it die honestly when it should.
  1. SkillTern

    The clearest version of the whole pattern: find the people a field forgot, then hand them the field. Curriculum, website, certification system — all of it built so the thing could outlive me, and then I stepped off. That was always the point, not the exit.

    2022–23 Taught 350+

  2. TurtleShell

    A tourist-safety app I co-founded: flag the blocks where people actually get hurt, then route you by what you came for — sightseeing or speed. The ending is the part I keep: killing it cleanly was harder than launching it, and more useful.

    2022–23 Shut down

  3. The correspondent layer

    The current chapter. A voice-and-email agent handling first-contact recruiting end-to-end, and the guardrails around every action it can take. It runs on a synthetic world, so the stamp reads Demo, not Live. The agents are the medium; how and why I run them is the point.

    2025– Demo

  4. Steering models

    The craft under the agent work — a.k.a. “manipulating the AI.” Getting reliable, exact, repeatable output from a people-pleasing text predictor: personas, hard rules, output contracts, and evals built to attack rather than flatter. Even the headline on this page was steered, not typed.

    2023– Ongoing

  5. AI Builder

    A cabin-design platform where the generator is the easy half. Around it sits a Seattle building-code rule engine, multi-objective optimisation that keeps the trade-off instead of burying it in a weighting, full plumbing and electrical routing, and export to the formats a plan reviewer actually opens. Generative design demos beautifully; this one has to survive the rules that decide whether a building can exist.

    2025 Prototype

  6. Teaching myself neuroscience in public

    Optogenetics, brain-computer interfaces, connectomics, and building a CNN from scratch — written up as I learned them. Not lab credentials; the autodidact’s habit of explaining a hard thing to make sure I actually understand it.

    2022–23 Four essays

  7. DeepTracer

    Real research plumbing in Dong Si’s lab: the unglamorous passes that feed the pipeline, and renders a structural biologist can actually argue with. Teaching a machine to read structure out of a blur is the same move as everything else on this list, pointed down a microscope.

    2025– Research

  8. The founder reflex, early

    Before any of it was a career: H2OAquatics (an AUV against ocean acidification), and civic platforms aggregating NGO campaigns. The instinct to build at a problem started young, and it started civic.

    2020–23 Civic

shaurya@sps — session.log
shaurya@sps ~ % grep -rl "same field" ~/built/
no matches
shaurya@sps ~ % ls ~/essays/
optogenetics/ bci/ connectomics/ cnn-from-scratch/ — self-taught neuroscience, written down where anyone can read it. 1,500+ views.
shaurya@sps ~ % ls ~/music/released/
empty — made often, released never. links when that changes, not before.
shaurya@sps ~ % echo $HOME
seattle ⇄ new delhi, depending on the month
shaurya@sps ~ %

That’s the short version. The long one — what I’m actually chewing on right now — is the part of this site I won’t fake, and it’s still being written.

Send the cold email — about the robot, the clean kill, the kids, or the music I haven’t released. The strange ones get answered first; worst case, a fast, honest no.