Stefan Vukanić, Developer in Belgrade, Serbia
Stefan is available for hire
Hire Stefan

Stefan Vukanić

Verified Expert  in Engineering

Software Developer

Belgrade, Serbia

Toptal member since April 12, 2016

Expertise
CLinuxPythonFlaskMachine LearningWindows DevelopmentDjangoMySQLMongoDBAWSBootstrapNLPC++
Bio

Stefan always strives for perfection regardless of the task at hand. Years of software development experience have made him highly adaptable to any working environment or framework. He also enjoys working with electronics, machine learning, and embedded systems.

Portfolio

Petnica Science Center
Robotics, Electronics
FNB
Apache Kafka, Spark, Apache Storm, MongoDB, Flask, Django
Freelance
Scikit-learn, C++, Python, NumPy, Scrapy, OpenCV

Experience

  • C - 5 years
  • C++ - 4 years
  • Python - 3 years
  • Flask - 2 years
  • JavaScript - 2 years
  • MongoDB - 2 years
  • MySQL - 2 years

Availability

Part-time

Preferred Environment

Git, Sublime Text, Linux

The most amazing...

...thing i've developed is a high throughput, distributed lead enrichment system for collecting, processing, and aggregating web data.

Work Experience

Teaching Assistant

2009 - PRESENT
Petnica Science Center
  • Assisted in the department of Applied Physics and Electronics.
  • Taught programming and electronics classes.
  • Managed and guided high school attendees on individual projects.
Technologies: Robotics, Electronics

Software Developer

2015 - 2016
FNB
  • Established a distributed enrichment system using Apache Storm, with Apache Kafka as the messaging back-end.
  • Coded distributed machine learning and natural language processing workflows using apache Storm, with Apache Cassandra as the back-end data store.
  • Built a RESTful website back-end powered by Flask.
  • Maintained and expanded the functionality of the existing Django app.
Technologies: Apache Kafka, Spark, Apache Storm, MongoDB, Flask, Django

Developer

2013 - 2015
Freelance
  • Developed image processing using openCV, such as banner removal and object detection.
  • Made data classification and clustering using support vector machines, k-means algorithm implemented using Scikit-learn and NumPy libraries.
  • Wrote efficient web crawlers for email gathering using Python Scrapy framework and Beautiful Soup.
  • Developed natural language processing software for correlating different news articles using a frequency-inverse document frequency approach.
Technologies: Scikit-learn, C++, Python, NumPy, Scrapy, OpenCV

Developer

2013 - 2013
Belgrade Science Fair
  • Developed a quad-copter's automatic stabilization from scratch, using inertial measurement unit with Kalman filtration implemented on PIC32 micro-controller.
Technologies: Electronics, Microcontroller Programming

Experience

APE Robotics

https://www.youtube.com/watch?v=7np0iNQzeoU
Part of the team that competed in the annual Eurobot robotics challenge. Worked on a high-level controller, implemented using ROS(Robot Operating System) framework, running on Beagle Bone Black, and powered by AM335 processor.

Handwritten Digit Classification

https://www.youtube.com/watch?v=4tiRFwCS3mo
Handwritten digit classification with an implementation from scratch of a neural network with back-propagation and stochastic gradient descent, running on TI's ARM Sitara.

Education

2009 - 2015

Bachelor's Degree in Telecommunications

University of Belgrade Faculty of Electrical Engineering - Belgrade

Skills

Libraries/APIs

Beautiful Soup, OpenCV, jQuery, NumPy, Scikit-learn

Tools

Eclipse IDE, Sublime Text, Git, Apache Storm

Languages

Python, C, C++, JavaScript

Frameworks

Flask, Django, Bootstrap, Storm, Spark, Scrapy, Knockout (Knockout.js), Apache Spark

Platforms

Linux, Amazon Web Services (AWS), BeagleBone Black, Windows, Apache Kafka

Paradigms

Object-oriented Programming (OOP), Distributed Programming, Concurrent Programming

Storage

MySQL, MongoDB, Cassandra

Other

Machine Learning, Microcontroller Programming, Electronics, Robotics, Natural Language Processing (NLP), Generative Pre-trained Transformers (GPT)

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