Gjorgji Madjarov, Developer in Skopje, Macedonia
Gjorgji is available for hire
Hire Gjorgji

Gjorgji Madjarov

Verified Expert  in Engineering

Machine Learning Developer

Skopje, Macedonia

Toptal member since February 1, 2016

Bio

Gjorgji is an accomplished researcher who has a wealth of software engineering experience with an extensive university background in machine learning, pattern recognition, data mining, information retrieval, and so on. He is a cooperative peer and an eager implementer who is capable of performing remarkable individual work to the highest standards and criteria. Gjorgji has exemplary communication skills and pays attention to details.

Portfolio

Elevate Global
ClickHouse, Elastic, Apache Flink, Python, Java

Experience

  • Machine Learning - 12 years
  • Java - 12 years
  • Data Mining - 10 years
  • SQL - 6 years
  • Recommendation Systems - 6 years
  • Deep Learning - 6 years
  • Apache Flink - 5 years
  • Stream Processing - 5 years

Availability

Part-time

Preferred Environment

C++, Python, Java

The most amazing...

...thing was making a platform that performs real-time data-stream analytics, anomaly detection/alerts, management, and predictive analytics of heterogeneous data.

Work Experience

CTO

2018 - PRESENT
Elevate Global
  • Worked on data stream processing and analytics.
  • Performed autonomous data-driven model generation, tuning, evaluation, ranking and selection of prescriptive models.
  • Developed an autonomous time-series forecasting solution that reduces the time and effort in modeling and forecasting energy parameters.
  • Built a monitoring-and-forecasting tool that enables IT infrastructure companies to perform faster and more accurate root-cause analysis, anomaly detection, smart alarming and to reduce the alert noise.
Technologies: ClickHouse, Elastic, Apache Flink, Python, Java

Assistant Professor

2012 - PRESENT
Faculty of Computer Science and Engineering, “St. Cyril and Methodius” University, Skopje, Macedonia
  • Designed and developed algorithms for multi-label learning and hierarchical multi-label learning.
  • Designed and developed algorithms for structured output prediction.
  • Applied deep learning to image classification and segmentation.
  • Analyzed text sentiment, speech synthesis, and recognition.
Technologies: SQL, .NET, Python, Java, C++

Research and Teaching Assistant

2007 - 2012
Faculty of Computer Science and Engineering, “St. Cyril and Methodius” University, Skopje, Macedonia
  • Developed algorithms for multi-class classification.
  • Researched along and with semi-supervision.
  • Performed structured output predictions and time-series predictions.
Technologies: SQL, .NET, C#, Java, C++, C

Software Engineer

2007 - 2007
Netcetera
  • Developed a real estate enterprise information system.
  • Worked on business logic.
  • Automated unit test generation.
  • Developed an extension of Apache Struts.
  • Worked with Hibernate ORM.
Technologies: Java

Learning from Massive, Incompletely Annotated, and Structured Data

Deals with image retrieval, deep learning, Twitter sentiment analysis, emotion identification on Twitter messages, and web genre predictions.

Twitter Sentiment Analysis Using Deep Convolutional Neural Network

With this, we can perform a Twitter sentiment analysis using a deep convolution neural network. The method is general and it can be applied on different short messages.

Content-based Image Retrieval for Large Medical Image Corpus

In this project, we address the scalability issue when it comes to content-based image retrieval in large image archives in the medical domain. Throughout the text, we focus on explaining how small changes in image representation, using existing technologies, leads to impressive improvements when it comes to image indexing, searches, and retrieval duration.

An Extensive Experimental Comparison of Methods for Multi-label Learning

This deals with a deep understanding of methods for multi-label learning. This evaluation is in the most cited papers in Pattern Recognition (one of the best artificial intelligence journals).

Evaluation of Different Feature Sets for Gait Recognition Using Skeletal Data from Kinect

In this project, we targeted the problem of gait recognition using skeletal data from Kinect.

Jozef Stefan Institue Research Visit

From 2010 to 2011, I researched about computer science at the Jozef Stefan Institue in Ljubljana, Slovenia.
2009 - 2012

PhD Degree in Computer Science

University Ss. Cyril and Methodius, Faculty of Computer Science and Engineering - Skopje, Macedonia

2007 - 2009

Master's of Science Degree in Computer Science

University Ss. Cyril and Methodius, Faculty of Electrical Engineering and Information Technology - Skopje, Macedonia

2002 - 2007

Bachelor of Science Degree in Computer Science and Electrical Engineering

University Ss. Cyril and Methodius, Faculty of Electrical Engineering and Information Technology - Skopje, Macedonia

Libraries/APIs

Java Collections, Standard Template Library (STL), Windows Forms (WinForms), X (formerly Twitter) API, POCO C++

Tools

Apache Maven, Elastic, Make, Makefile

Languages

C++, Java, SQL, C, Python, Python 3, C#

Paradigms

Object-oriented Design (OOD), Object-oriented Programming (OOP), Agile Software Development

Platforms

Apache Flink

Frameworks

Spark Structured Streaming, ASP.NET, .NET, Spring

Storage

SQLite, MySQL, ClickHouse, PostgreSQL

Other

Decision Trees, Machine Learning, Recommendation Systems, Data Mining, Pattern Recognition, Deep Learning, Stream Processing

Collaboration That Works

How to Work with Toptal

Toptal matches you directly with global industry experts from our network in hours—not weeks or months.

1

Share your needs

Discuss your requirements and refine your scope in a call with a Toptal domain expert.
2

Choose your talent

Get a short list of expertly matched talent within 24 hours to review, interview, and choose from.
3

Start your risk-free talent trial

Work with your chosen talent on a trial basis for up to two weeks. Pay only if you decide to hire them.

Top talent is in high demand.

Start hiring