Open to Software, Backend, Data & AI rolesAvailable now

I build practical software, data & AI systems — Python-first.

I build backend services and LLM-powered systems with Python and FastAPI — REST APIs, RAG and semantic search, OCR pipelines, and vector/graph databases. I co-founded Lucid, an AI study app now live on the App Store, and shipped production work at Neurosoft.

Wrocław, PolandCo-Founder & Backend Engineer at Lucid

Python + FastAPI

Backend services, REST APIs, and data workflows

RAG / LLM systems

Retrieval, semantic search, OCR, and orchestration

Shipped to production

App Store app + production work at Neurosoft

Co-Founder & Backend Engineer at Lucid

Backend systems + data workflows + practical AI

Selected work

What I optimize for

Clean APIs, reliable data flows, readable architecture, and AI features that solve real user problems.

PythonFastAPISQLRAGOCRNeo4j

Live

on the App Store

Lucid AI study app, Education category, 12 languages

200+

backend tests

pytest unit + integration coverage on Lucid

10k+

traffic samples

Processed through Python pipelines at Neurosoft

85%+

trace-match accuracy

Vehicle trace matching for an ITS product

About

Backend, data, and AI engineering with a product mindset

I like building practical systems end to end: defining the data flow, designing the API, choosing the database, connecting AI or ML components when they add value, and making the result usable for real people.

CO

Caner Olcay

Software / AI Engineer

Open to workBackendData & AI
Wrocław, Poland
Co-Founder & Backend Engineer at Lucid
Wrocław University of Science and Technology

Looking for

Open to Software Engineer, Python Developer, Backend Developer, Data/AI Engineer, and ML Engineer roles

How I work

Most of my projects start with a concrete workflow: user input, API endpoints, storage, processing, and a clear way to return useful results.

My strongest areas are Python backend development, FastAPI services, SQL databases, data processing, RAG systems, OCR workflows, and applied machine learning.

What matters to me

  • Clean APIs that are easy to use and maintain
  • Reliable data flows from input to storage to output
  • Readable architecture that can grow with the product
  • AI features that solve real user problems

Backend & APIs

Python services that expose clear REST APIs, handle auth, and connect users to useful data.

FastAPIRESTJWT Auth

Data Workflows

SQL, vector, and graph stores plus ETL pipelines that keep application data reliable.

PostgreSQLpgvectorPrefect ETL

Applied AI Features

RAG, OCR, semantic search, and ML components when they solve a real product problem.

RAGOCRLangGraph
Experience

Production work, not just side projects

I've shipped real systems end to end — a backend powering a live App Store app, computer vision in a production traffic product, and a knowledge-graph RAG assistant.

Lucid (uselucid.app)

Current

Co-Founder & Backend Engineer

Jan 2026 - Present

Remote

Co-founded an AI study app now live on the App Store and built its FastAPI backend end to end.

  • Co-founded and built the backend for Lucid, an AI study app live on the App Store (Education category, localized in 12 languages): a FastAPI service with 20+ REST endpoints covered by 200+ unit and integration tests (pytest)
  • Developed the core OCR-to-retrieval pipeline: Google Vision OCR -> OpenAI embeddings (1536-dim) -> pgvector with HNSW indexing -> LLM-based answer, flashcard, and quiz generation
  • Implemented JWT authentication with Supabase, row-level security, per-user rate limiting (100 req/min), and async background processing across the full product from backend architecture to release
PythonFastAPIPostgreSQLpgvectorSupabaseOpenAIDocker

Solvro

Current

Machine Learning Engineer

Nov 2025 - Present

Wrocław, Poland

Software Development Student Group. Building a Knowledge Graph RAG assistant for the ToPWR university app.

  • Built a natural-language-to-Cypher retrieval assistant over a Neo4j knowledge graph, served through a FastAPI backend and an MCP (Model Context Protocol) server
  • Designed a LangGraph pipeline with LLM guardrails for query routing, Cypher generation, and response orchestration, deployed as a 4-service Docker stack (React, FastAPI, MCP, Neo4j)
  • Implemented a Prefect-based ETL pipeline ingesting PDF and text documents into the knowledge graph via OCR, text extraction, and LLM-generated Cypher
PythonFastAPILangGraphNeo4jFastMCPPrefectDocker

Neurosoft

AI Software Engineer (Intern)

Aug 2025 - Oct 2025

Wrocław, Poland

Computer-vision and ML work inside a production intelligent-transportation system.

  • Processed and analyzed 10,000+ traffic-scene samples through Python data pipelines for a production intelligent-transportation system
  • Improved vehicle trace-matching accuracy to 85%+ through algorithm refinement and validation
  • Developed computer-vision and ML components integrated into the company's traffic-monitoring product
PythonOpenCVPyTorchNumPyPandas
Selected work

Projects across backend, data, and applied AI

Each project shows a practical problem, what I built, the stack behind it, and the result or impact where available.

Backend / AI PlatformLive on App StoreCo-Founder & Backend Engineer

Lucid - AI Study App

FastAPI backend powering an iOS app live on the App Store: 20+ REST endpoints, OCR-to-RAG pipeline, and 200+ tests.

Problem

Helps students turn lecture screenshots and notes into searchable study material, flashcards, and quizzes.

What I built

Built a backend that accepts lecture images, extracts text with OCR, generates embeddings, stores notes, and enables semantic search, AI Q&A, flashcards, and quizzes.

Impact

iOS app live on the App Store, 12 languages, 200+ backend tests

PythonFastAPIPostgreSQLpgvectorSupabaseGoogle Vision OCROpenAI
Backend / Data RetrievalProduction buildMachine Learning Engineer

Knowledge Graph RAG (ToPWR)

FastAPI + Neo4j + LangGraph + MCP workflow that turns natural language into Cypher, deployed as a 4-service Docker stack.

Problem

Helps students and staff query university information spread across pages, departments, and systems.

What I built

Built a knowledge-graph retrieval workflow that checks query relevance, generates Cypher, executes graph retrieval, and returns answers through an application API.

Impact

Natural language mapped to graph-backed university data, in production at Solvro

PythonFastAPILangGraphLangChainFastMCPNeo4jPrefectDocker

More builds and experiments

Additional work across computer vision, RAG, and research / forecasting.

Computer Vision / 3D

2025

NeuroPark - 3D Vehicle Detection

Reconstructs 3D vehicle scenes from a single traffic-camera image, validated against LiDAR.

YOLOv8MiDaSOpenCVPyTorch

Validated monocular 2D-to-3D reconstruction, presented at KPZ25

Backend / RAG Prototype

2024

Medical Chatbot RAG

Provides educational health Q&A from retrieved source content instead of free-form LLM answers.

PythonFlaskLangChainPinecone

End-to-end retrieval app with containerized AWS deployment

Research / Forecasting

2024

TensoCast - Traffic Forecasting

Forecasts traffic patterns from multidimensional sensor data.

PythonPyTorchNumPyScikit-learn

35% improvement over baseline approaches

Stack

Backend, data, and AI tools I work with

My core stack is Python, FastAPI, SQL, PostgreSQL, and practical AI tooling for RAG, OCR, semantic search, and computer vision.

Backend & APIs

Python application services that expose clear APIs and connect product workflows.

Core

FastAPI

Async Python backend services

Flask

Lightweight Python services

REST + JWT

Endpoint design and auth

Pydantic

Validation and schemas

SQLAlchemy / Alembic

ORM and migrations

AI / ML Systems

Applied AI for retrieval, document understanding, search, and perception.

Strong

RAG

Retrieval-augmented workflows

LangChain / LangGraph

Stateful AI orchestration

MCP

Model Context Protocol servers

OCR

Text extraction from images

Computer Vision

YOLO, OpenCV, PyTorch

Databases

Storage and retrieval tools for structured, graph, and vector data.

Strong

PostgreSQL

Relational application data

pgvector

Vector search inside PostgreSQL

Neo4j

Graph data and Cypher retrieval

Pinecone

Managed semantic vector search

Supabase

Auth, storage, and RLS

Languages & Tools

Everyday languages and tooling for build, test, deploy, and collaborate.

Working

Python / SQL

Primary languages (C++, R basics)

Docker

Portable multi-service environments

Git + CI/CD

GitHub Actions pipelines

Linux

Ubuntu server environments

AWS / GCP / Azure

EC2, S3, and cloud hosting

Credentials

Education, certifications, and languages

Formal engineering education in Wrocław, backed by specialized ML and MCP certifications and a multilingual background.

Education

B.Eng. in Electronics & Computer Engineering

Wrocław University of Science and Technology

Wrocław, Poland

Expected July 2026

Certifications

  • Machine Learning Specialization

    2025

    Stanford University & DeepLearning.AI

  • MCP for Production Automation

    2025

    Hugging Face

Languages

  • EnglishFluent (C1)
  • TurkishNative
  • PolishBasic (A1, learning)
Contact

Let's build something useful

I'm especially interested in roles where I can work with Python, APIs, databases, data workflows, and practical AI/ML features.

Best fitPython, backend, data, applied AI

Software, backend, data, and AI work where I can build useful systems

Open to Software Engineer, Python Developer, Backend Developer, and Data/AI & ML Engineer roles. Reach out and let's talk.

Python backend services

APIs, databases, and data workflows

Applied AI / ML features

RAG, OCR, semantic search, and CV

Availability snapshot

Open to Software Engineer, Python Developer, Backend Developer, Data/AI Engineer, and ML Engineer roles

Wrocław, Poland