Piotr Obiegły

language + code + ai

Piotr Obiegły

Applied AI & Language Technology

RAG • Document AI • LLM Applications | EN-PL Localization

Building practical AI systems at the intersection of language, software, and structured knowledge.

Poznan, Poland. Open to Python, applied AI, and language technology roles.

View projects Get in touch

Current focus

The areas connecting my localization background with practical AI and data work.

  • AI and NLP systems

    Building practical workflows around LLMs, prompt design, structured outputs, and production-minded language applications.

  • Python for language tooling

    Using Python to turn language services into reusable automation, data workflows, and application logic.

  • Data analysis and decision-making

    Applying exploratory analysis, notebook workflows, and structured thinking to product, model, and operational decisions.

  • Multilingual product quality

    Bringing localization expertise into QA, taxonomy, terminology systems, and user-facing precision across digital products.

Selected projects

Selected work across Document AI, applied AI products, and language technology.

Beta

PDF-to-JSON RAG

Built a local-first Document AI system that converts PDFs into structured JSON, indexes document-aware chunks, and answers multi-document questions with page-level citations. It supports native-text extraction, OCR fallback, quality diagnostics, a web UI and CLI, and reproducible retrieval benchmarks.

It turns messy document collections into inspectable, queryable data while validating extraction and retrieval quality instead of trusting unverified outputs.

  • Python
  • OCR
  • ChromaDB
  • RAG
  • CLI
  • Evaluation
Open project Live demo

Ongoing

ShortsAI outfit planner

Building a weather-aware outfit planner for runners, walkers, and everyday outdoor plans. The app combines live forecast data, activity timing, return-home conditions, and personal comfort feedback into a clear clothing recommendation.

Shows applied AI product engineering: deterministic recommendation logic selects the outfit, while AI explains the already locked result instead of inventing advice.

  • Next.js
  • TypeScript
  • Expo
  • Supabase
  • Open-Meteo
  • OpenRouter
Open project

Ongoing

Crypto.com localization

Managing Polish-language localization across Crypto.com's Web3 platform, including website and mobile wallet. Focused on terminology consistency, UX clarity, and trust-building across high-risk financial content.

Sustained quality ownership across high-stakes fintech surfaces where precision affects trust, comprehension, and conversion.

  • Localization
  • Web content
  • Mobile product copy
  • Terminology
See all projects

Learning snapshot

Selected courses and certifications focused on LLMs, Python, data analysis, and applied AI development.

AI_devs

2026

AI_devs 4 Builders

Large Language Models (LLMs), Prompt Engineering, LLM applications

DeepLearning.AI

2026

LLMOps

LLM evaluation, fine-tuning, LLMOps, production AI workflows

See all courses and certifications

Open to collaboration

Building at the intersection of language and AI?

If the work needs both technical structure and multilingual judgment, I would be glad to talk.

Start a conversation