Software Engineer · CS student

Anton
Rudnytskyi.

Building intelligence
into real products.

Anton Rudnytskyi is a software engineer and Computer Science student at the University of Nebraska at Omaha, building applied AI products, backend systems, and production infrastructure.

Omaha, Nebraska, USA
AR

Currently building at Bar-IQComputer Science at the University of Nebraska at Omaha

Scroll to explore
20+Projects built
7Bar-IQ pilot locations
3.76CS GPA at UNO
From first commit to productiongithub.com/rudnytskyi1
01 / About

About

A little context behind the code.

For the past two years I've been an engineer at a computer-vision startup, taking the product from ML models to production infrastructure. I study Computer Science at the University of Nebraska at Omaha and focus on applied AI, backend systems, and infrastructure.

I was born in Ukraine and moved to the US as a teenager. I've been programming since childhood and started competing in programming olympiads in Ukraine. Today I work at the intersection of AI and production engineering: training and fine-tuning models, building backends, and deploying systems that real users rely on. Long term, I'm interested in using AI to improve public services and government.

LanguagesEnglish / Ukrainian / Russian

Education & certification

UNIVERSITY

University of Nebraska at Omaha

B.S. Computer Science

  • GPA: 3.76
  • Second-year student working toward an early graduation in December 2027.
  • Course load: two semesters at 18 credit hours and one at 16.
  • Considering a Mathematics minor.
CERTIFICATION

Oracle Certified Associate

Java SE 8 Programmer I

  • Certification: 1Z0-808
RESEARCH

Undergraduate research

Prof. S. Song · University of Nebraska at Omaha · 2026–27

Secure messaging project, moving toward AI/LLM work.

02 / Experience

Experience

Building systems that make it into production.

  1. Aug 2024 — Present

    Remote

    Current role

    Bar-IQ

    Software Engineer

    Computer-vision inventory system for bars and restaurants.

    • Designed, built, and deployed the full product, from ML models to production infrastructure; running a production pilot across 7 bar locations.
    • Fine-tuned SAM-family segmentation models with LoRA to estimate liquid levels in bottles from photos, with 97%+ volume-estimation accuracy.
    • Built and deployed the production backend: FastAPI, PostgreSQL (AWS RDS), S3, Stripe billing, and serverless GPU inference.
    • Built a native iOS app in Swift with NFC-based inventory scanning, after an early React Native/Expo prototype, plus an analytics platform for multi-location management.
  2. Aug 2023 — May 2024

    Gainesville, GA

    Gainesville City Board of Education

    Software Developer Intern

    • Developed software to streamline Chromebook distribution and returns across schools.
    • Updated and maintained Chromebook software for students.
03 / Selected Projects

Selected Projects

Top 5 of 20+ projects I've built over the years — from production AI systems to iOS apps and developer tools.

01 / Retrieval & evaluation
~98,000 indexed chunks44 sites / 162 test questions
Retrieval & evaluation

MPS School Information Chatbot

AI assistant that answers staff and family questions about Millard Public Schools (Omaha, NE), using only the district’s own published websites and documents.

  • Team project for Millard Public Schools District Office, with a retrieval pipeline and evaluation system. About 98,000 indexed chunks from district and school sites, PDFs, Drive files, and calendars, rebuilt with one command after a refetch.
  • Hybrid vector and BM25 search, per-school partitions, LLM reranking, cited answers, and a fact-checking pass. The bot says ‘I don’t know’ instead of guessing.
  • A 162-question test set with a 3× LLM judge and cost tracking. An A/B test selected a reranker with the same measured quality, about 9% lower cost, and about 2× faster responses.
  • Python
  • OpenAI API
  • Claude Haiku
  • OpenRouter
  • ChromaDB
  • BM25
  • Flask/SSE
  • SQLite
  • Selenium
  • PyMuPDF
  • Ollama
  • pytest
View project
02 / Developer tools
Plan → Build → ReviewLead model + worker models
Developer tools

multiagents — Claude Code Plugin

A multi-agent coding workflow that cuts AI coding costs.

  • A lead model plans tasks and reviews code, while low-cost worker models write the code.
  • Used by the team at my company.

UpdateThe project is evolving into a Claude Code + Codex orchestration plugin.

  • LLM agents
  • developer tools

Private repository

View project
03 / Personal AI
RTX 5090Room clients ↔ GPU hub
Personal AI

Rowan — Multi-room AI Home Assistant

A personal AI assistant that hears, sees, and controls my room.

  • GPU hub (RTX 5090) running real-time speech recognition (faster-whisper), speaker identification, face recognition, YOLO11 and SAM3 vision, a local LLM with tool calling, and text-to-speech.
  • Room clients handle wake word, camera, and control of lights and the PC over WebSocket.
  • Python
  • asyncio
  • WebSocket
  • computer vision
  • local LLM
View project
04 / Native iOS
Read. Translate. Understand.Swift / iOS
Native iOS

Bible Reader — iOS App

An English Bible reader for non-native speakers with instant translation and AI explanations.

  • Tap any word or verse for an instant translation.
  • Ask an AI assistant questions about the context of a passage.
  • Swift
  • iOS
  • LLM

Personal app · Not on the App Store

View project

Also built: a geopolitical strategy simulator (in progress; Python, FastAPI, CesiumJS, Electron, local LLM), a football prediction-league API (FastAPI, PostgreSQL), and many more.

04 / On GitHub

On GitHub

Live public activity from @rudnytskyi1.

05 / Toolkit

Toolkit

The tools I use to take an idea from model to deployment.

01

Languages

  • Python
  • Swift
  • Java
  • JavaScript/TypeScript
  • SQL
02

AI/ML

  • Computer vision
  • LoRA fine-tuning
  • SAM
  • YOLO
  • Whisper
  • LLM tool use
03

Backend & cloud

  • FastAPI
  • PostgreSQL
  • AWS (RDS, S3)
  • Serverless GPU inference
  • Stripe
  • Git
04

Familiar with

  • React
  • React Native
  • PHP
06 / Recognition

Recognition

From programming olympiads in Ukraine to team competitions in the US.

  • 011st place, City Programming Olympiad (Ukraine)
  • 0227th of ~1,000, Kyiv Programming Olympiad (Ukraine)
  • 032nd place, ACTE Georgia State Team Coding Competition (USA)
  • 043rd place, Hall County Schools Team Coding Competition (USA)
  • 05Inspirit AI (Stanford/MIT) program participant
07 / Let's connect

Let's connect