Senior full-stack Rails engineer, 9 years commercial. I ship AI features into
production SaaS — not demos.
Most recent: Review Copilot, an AI review-analytics app live on the Shopify App
Store, built and shipped solo end to end. Rails 8 backend, plus a DistilBERT
multi-label classifier I fine-tuned via knowledge distillation and serve from a
Python/FastAPI microservice, orchestrated through Sidekiq. Every recommendation
cites the reviews behind it, with a verification pass that flags claims the
underlying feedback doesn't support.
Before that: an AI-driven ABM platform (Rails + React) with LLM content-generation
pipelines, marketplace products with payments and geolocation, and a legacy
CoffeeScript → Turbo Frames migration.
Looking for senior IC work on a Rails product — ideally somewhere LLM or ML
features are on the roadmap rather than bolted on.
katatsu12 · · focus · HN ↗
Remote: Yes
Willing to relocate: No
Technologies: Ruby, Ruby on Rails, PostgreSQL, Sidekiq/Redis, Hotwire, JavaScript, TypeScript, React, GraphQL/REST/Grape, RSpec/Capybara, Python/FastAPI, PyTorch/Hugging Face, LLM APIs (OpenAI, Anthropic), Docker, AWS/DigitalOcean
Résumé/CV: <a href="https://katatsu12.github.io/" rel="nofollow">https://katatsu12.github.io/
Email: den.zubrytskyi@gmail.com
---
Senior full-stack Rails engineer, 9 years commercial. I ship AI features into production SaaS — not demos.
Most recent: Review Copilot, an AI review-analytics app live on the Shopify App Store, built and shipped solo end to end. Rails 8 backend, plus a DistilBERT multi-label classifier I fine-tuned via knowledge distillation and serve from a Python/FastAPI microservice, orchestrated through Sidekiq. Every recommendation cites the reviews behind it, with a verification pass that flags claims the underlying feedback doesn't support.
Before that: an AI-driven ABM platform (Rails + React) with LLM content-generation pipelines, marketplace products with payments and geolocation, and a legacy CoffeeScript → Turbo Frames migration.
Looking for senior IC work on a Rails product — ideally somewhere LLM or ML features are on the roadmap rather than bolted on.