Skip to content
View MariaVlahova's full-sized avatar

Block or report MariaVlahova

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
MariaVlahova/README.md

Hi, I'm Maria — Backend, Data & ML Engineer

I build production-grade APIs, data pipelines, and AI systems for businesses.

If you're looking for someone who can own a project end-to-end — architecture → development → deployment — I can help.
Most of my freelance clients come to me when they need a reliable developer who understands both backend engineering and machine learning, and can deliver clean, scalable, production-ready systems.


🔧 What I Help Clients Build

Backend & API Development

  • FastAPI, Django, DRF
  • Authentication systems (JWT, OAuth2, SSO)
  • High-performance REST APIs
  • Microservices, async processing

Data Engineering

  • Spark + Kafka streaming/batch pipelines
  • Parquet/Delta Lake workflows
  • Distributed processing, data quality, schema evolution
  • Kubernetes, Docker, S3

Machine Learning / AI

  • End-to-end ML pipelines (training → inference)
  • Computer vision, classification, recommendations
  • FastAPI ML serving, monitoring, automation

I focus on building systems that are stable, maintainable, and ready for real users — not quick prototypes that fall apart.


🚀 Highlight Projects (What Clients Usually Look At)

AI Presentation Analyzer

Deep-learning system that analyzes slide decks and generates recommendations.
Skills: TensorFlow, Python, FastAPI, Docker

Authentication Server

Centralized JWT + OAuth2 identity provider with 36+ documented endpoints.
Skills: Django, DRF, PostgreSQL, Docker

Django + FastAPI Hybrid Backend

Unified CMS + API platform for a production website.
Skills: Wagtail, Django, FastAPI, Uvicorn

Kafka → Spark → Parquet Pipeline

Schema-aware ingestion pipeline with batch/stream processing.
Skills: Spark, Kafka, Kubernetes, Hive Metastore

➡️ Pinned repositories include code, architecture, and examples.


🧭 My Company

I also co-run Codea, where we build end-to-end software solutions for clients — from backend infrastructure to AI-powered systems.

🌐 Website: https://codea.bg


📬 Work With Me

I take on freelance projects involving:

  • Backend/API development
  • ML engineering
  • Data pipelines
  • System architecture
  • Automation tools

Open to short-term contracts, long-term consulting, or full project delivery.


📫 Contact

Let’s build something solid and scalable.

Pinned Loading

  1. databricks-kafka-pipeline databricks-kafka-pipeline Public

    End-to-end streaming pipeline with Kafka ingestion, automatic schema inference, and Bronze-Silver-Gold Delta layers. Supports continuous or batch runs via a flexible orchestrator. Modular, Git-frie…

    Python

  2. text-image-coherence-dataset-generator text-image-coherence-dataset-generator Public

    Generates datasets of presentation slides and their accompanying text. Each image–text pair is evaluated for coherence, with a label indicating whether the slide and text match (true) or not (false…

    Python 1

  3. UrbanHazardDetector UrbanHazardDetector Public

    A Python tool for detecting buildings, amenities, and sports infrastructures located near/on natural hazard

    Python

  4. codea-website codea-website Public

    This repository contains Codea Blog, a production-grade hybrid content platform that merges Django + Wagtail CMS with FastAPI into a single unified ASGI application. It serves as a case study demon…

  5. ai_presentation_analyzer ai_presentation_analyzer Public

    Analyzes presentation quality, style coherence, and provides personalized recommendations using three deep learning modules. Integrates all components through a unified PostgreSQL database with a m…

    Jupyter Notebook

  6. codea-auth-server codea-auth-server Public

    Production-ready Django REST Framework authentication server case study. Features JWT auth, Google OAuth, OAuth 2.0 provider, role-based access control, encrypted token storage, rate limiting, heal…