Skip to content
View Skits0098's full-sized avatar
  • TurtlesEgg
  • Naples, FL

Block or report Skits0098

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Skits0098/README.md

Kiran Shelar

AI product engineer in Naples, FL. I build LLM applications, AI agents, and the tooling to evaluate them.

Production work

Most of my production work is private and proprietary to TurtlesEgg Inc. I'm happy to walk through architecture and code in an interview.

  • AI marketing operations platform: multi-agent system for brand-aware content generation, SEO articles, approvals, scheduling, analytics, and publishing across eight channels. In daily use by the team.
  • LLM product categorization pipeline: batch LLM workflow with human approval and reversible changes. 20x+ throughput on imports of tens of thousands of listings.
  • There: Calorie Counter & Gym: iOS and Apple Watch app in Swift with HealthKit and an opt-in AI coach. App Store

Open source

  • OpenParity: statistical testing for LLM evals. Tells you whether a change between two eval runs is real or noise, using paired tests, TOST equivalence gating, cluster-robust intervals, and power analysis. Pre-release.

Stack

Python, TypeScript, Node.js, React, Swift, LLM APIs, GitHub Actions, Linux, Cloudflare

Contact

LinkedIn

Pinned Loading

  1. OpenParity OpenParity Public

    Is that eval regression real, or just noise? OpenParity does the statistics every LLM eval tool skips: paired testing, equivalence gates (TOST), cluster-robust intervals, and power analysis. Not an…

    Python