Projects
Case studies
Each case shows in a minute what changed: before and after, the effect of the approach in numbers and an interactive model of the system — with the full engineering write-up one click away.
Case 01 · AI Engineering / Backend / Vector Search
Intelligent Knowledge Base
A RAG system for searching corporate knowledge
The system answers natural-language questions from an organisation's internal documents: it finds relevant fragments with vector search and hands them to a language model as context.
Python · FastAPI · PostgreSQL + pgvector · Milvus · Redis · LLM API
Open the caseCase 02 · Data Engineering / Scientific Computing / Python
Scientific Data Processing
Numerical processing, interpolation and visualisation of data
Software tools for numerical data: preparing datasets, numerical methods and interpolation, and plots that compare the original and the processed values.
Python · NumPy · SciPy · Pandas · Matplotlib
Open the caseCase 03 · Backend / Automation / Systems Integration
Business Process Automation
A platform for business process automation and integrations
Software that removes manual work: it takes data from several sources, checks and processes it, runs tasks and hands the results to other services.
Python · Django · RabbitMQ · REST API
Open the caseCase 04 · Networking / Backend / Client-Server Architecture
Internal Corporate Messenger
A corporate messaging system on Python sockets
A private messenger for employees inside an organisation. The core of the project is networking: clients exchange messages through a server over TCP connections, and UDP is used where it fits.
Python · Sockets · TCP · UDP
Open the caseCase 05 · Distributed Systems / Backend Architecture
Event-Driven Backend Architecture
Asynchronous event processing and service-to-service communication
Server-side architectures where components talk through message brokers and work is done asynchronously, by background handlers and event consumers, rather than inside one HTTP request.
Python · FastAPI · RabbitMQ · Apache Kafka · Redis · PostgreSQL
Open the caseCase 06 · Full-Stack Development / Commercial Web
Full-Stack Web Applications
Complete web applications and websites built to order
Client web solutions end to end: the interface, server-side logic, integrations and the database — a finished product rather than a standalone API.
React · Next.js · Python · Django · FastAPI · Flask · PostgreSQL
Open the caseCase 07 · Cloud / Database Engineering / Backend
Cloud & Data Infrastructure
Cloud infrastructure and data storage systems
Working with cloud databases and storage: data structure, connecting backend applications, relational data, vector search and caching — each in the store that fits it.
Python · PostgreSQL · Redis · pgvector · Milvus · Cloud databases
Open the caseCase 08 · Automation / Backend / Integrations
Bots & API Integrations
Smart bots and automated services
Bots and automated programs that talk to users, external APIs and internal systems. A bot here is not a message window but a software system with business logic, state and integrations.
Python · Flask · REST API · PostgreSQL · Redis · LLM API
Open the case
AI Workflow
AI-assisted Software Engineering
I use OpenAI Codex and Claude as development tools. Architectural decisions, checking the result and responsibility for the code stay with me.
01
Framing the task
I give an AI agent a task the way I would write a spec: context, constraints and a definition of done.
02
Architecture and decomposition
I work out the architecture first and split a complex task into steps that can each be checked on their own.
03
Technical specifications
I prepare specifications that the work follows in iterations.
04
Existing code
I use AI to analyse and refactor existing code.
05
Checking the result
Every result goes through review, tests and a real run. I accept only what I understand and can explain.
06
Part of the process
I fit AI tools into the workflow so they speed development up without lowering the quality.
OpenAI Codex · Claude · Python · TypeScript
AI speeds the work up but makes no decisions: the engineer is accountable for the architecture, the quality and the final result.