Data Scientist & AI Engineer
I build data-driven and AI-powered applications, turning ideas into working products. Data Science, Machine Learning and AI Engineering — from initial concept to production.
01
Predictive models, statistical analysis and data-driven solutions.
02
AI applications, LLM-based systems, agents and intelligent workflows.
03
Python applications, APIs, web applications and production-ready software.
04
Turning ideas into functional prototypes and MVPs quickly.
05
Taking prototypes beyond experimentation and turning them into usable software products.
Selected work
Problem — A multi-step process handled manually, with information spread across several tools and data sources.
Solution — An agent that plans the task, calls the right tools, reads external data and completes the workflow end to end, with a human checkpoint where it matters.
Python · LLM APIs · Agent framework · FastAPI
Problem — Knowledge locked inside documents that are slow to search and hard to query in natural language.
Solution — Documents are chunked and embedded; questions retrieve the most relevant passages, and the answer is generated with references to the sources.
Python · Embeddings · Vector database · LLM APIs · Streamlit
Problem — A decision that depended on intuition and spreadsheets, with historical data available but unused.
Solution — A supervised model trained on historical data, wrapped in an application that non-technical users can run and understand.
Python · Pandas · scikit-learn · Streamlit · Azure ML
Not all professional work is public. Production solutions built for companies are available as case studies on request.
All work →Open source & code
Selected projects and technical experiments are available on GitHub.
TODO_PLACEHOLDER/rag-assistant
Retrieval-Augmented Generation assistant: ingestion, vector search and grounded answers.
Python · LLM · Vector DB
GitHub ↗TODO_PLACEHOLDER/ml-experiments
Technical experiments and reusable utilities for data science and model evaluation.
Python · scikit-learn · Pandas
GitHub ↗Private project
Production AI solution developed for a client/company. Details available upon request.
Python · LLM · APIs
Private · details on requestHow I work
01
Understand the problem, data and business goal.
02
Develop the prototype and validate the technical approach.
03
Improve the solution based on feedback and real-world usage.
04
Turn the validated solution into a working application.
Fast development without sacrificing engineering quality.
Services
From Concept
→ working prototype
From ML model
→ usable application
From Manual workflow
→ AI-powered automation
Contact
Let's discuss it.