Python Developer | AI & Big Data

I'm studying AI and Big Data. Looking for a Junior Python Developer position — I prefer projects involving data, ML or backends, but interested in any Python-related work.

I build solutions in Python, combining AI & Big Data fundamentals with practical engineering:

• LLM-based assistants (RAG, agents, prompting)
• Data and ML pipelines (ETL, training, monitoring)
• REST APIs and backend systems (FastAPI, async)
• Data analysis and dashboards (pandas, SQL, Streamlit)
• Full-stack applications integrating data with AI modules

• Python (3.10+, async/await, pydantic, pytest)
• SQL (PostgreSQL, JOINs, CTEs, window functions, optimization)
• Machine Learning (scikit-learn, pandas, numpy, embeddings, RAG)
• LLM & GenAI (Azure OpenAI, LangChain, prompt engineering, cost optimization)

• Azure (Azure OpenAI, AI Search, Container Registry, App Service)
• Docker (image building, networking, volumes, docker-compose)
• MLOps (DVC, MLflow registry, model versioning, drift monitoring)
• CI/CD (GitHub Actions, basic automation)

• FastAPI (REST endpoints, Pydantic models, dependency injection, async)
• Streamlit (rapid prototyping, dashboards, data apps)
• React (components, hooks, API integration — supporting)
• Git, PostgreSQL, Jupyter, VS Code, Linux/Bash

Q&A assistant on PDF/CSV documents. Powered by Azure OpenAI (gpt-4o-mini ~$1/1000 queries) and Azure AI Search.

Stack: Azure OpenAI, Azure AI Search, LangChain, Streamlit, Python
What I learned: RAG patterns, Azure integration, cost optimization, hybrid search
Link: github.com/UnuntriDev/azure-rag

End-to-end MLOps pipeline for predicting apartment prices. DVC + MLflow registry + FastAPI + drift monitoring + conformal prediction intervals.

Stack: DVC, MLflow, FastAPI, Streamlit, scikit-learn, PostgreSQL
What I learned: Production ML pipeline, model versioning, monitoring, API deployment
Link: github.com/UnuntriDev/Price-predictor

Portfolio analysis and investment risk assessment dashboard. Streamlit + real-time financial data.

Stack: Streamlit, pandas, numpy, yfinance, plotly
What I learned: Data visualization, financial metrics, portfolio analysis
Link: github.com/UnuntriDev/Finport

Full-stack data cleaning application. Smart Fix (auto-detect issues), async jobs, before/after diffs.

Stack: Python (backend), React + TypeScript (frontend), async jobs
What I learned: Full-stack thinking, async programming, UI/backend integration
Link: github.com/UnuntriDev/data-cleaner

• Deep SQL (advanced queries, explain plans, indexes, optimization)
• LangChain & Agents (tool calling, ReAct loops, memory management)
• Azure deeper (Functions, Container Apps production setup, cost management)
• FastAPI Advanced (middleware, background tasks, websockets)

• LinkedIn: https://www.linkedin.com/in/arkadiusz-tokarczyk
• Email: ununtridev@gmail.com
• GitHub: @UnuntriDev
• Location: Kraków

• Python is my main — I prefer it for everything
• Interested in Big Data, data pipelines, analytics
• Learning Azure, but open to AWS/GCP
• Fascinated by LLMs and AI, but also solid backend & data infrastructure
• For every problem I ask: "how do I scale it, automate it, monitor it?"
• Prefer learning by building — more projects, fewer tutorials