Andrija is available for hire

Andrija Djurisic

Verified Expert in Engineering

Machine Learning Developer

Location

Belgrade, Serbia

Toptal Member Since

February 6, 2017

Andrija is a talented software engineer and a machine learning researcher. He holds a master of science degree in computer science and mathematics and has 12 years of professional experience. Andrija has a strong track record in shipping AI products as well as doing cutting-edge research.

Statistics Data Engineering Machine Learning Deep Learning Deep Neural Networks Artificial Intelligence (AI)Computer Vision Ubuntu SQL JSON XML OpenCV C++Python Unix

Portfolio

Trendage, Inc.

PyTorch, Ubuntu, Artificial Intelligence (AI), Deep Neural Networks...

Ydrive

PyTorch, C++, Ubuntu, Artificial Intelligence (AI), Deep Neural Networks...

Lotusflare

C++, Ubuntu, ClickHouse, Redis, Cassandra, Python, Lua, SQL...

Experience

C++ - 7 years Python - 7 years Machine Learning - 6 years Deep Learning - 5 years Computer Vision - 4 years PyTorch - 4 years TensorFlow - 4 years Reinforcement Learning - 4 years

Availability

Full-time

Preferred Environment

PyTorch, Ubuntu, Git, PyCharm, TensorFlow

The most amazing...

...thing I've developed is an outfit recommendation engine that mimics professional stylists.

Work Experience

Senior Machine Learning Engineer

2019 - 2024

Trendage, Inc.

Implemented a virtual try-on pipeline using diffusion models. Work included all aspects of development, from setting up distributed large-scale training to serving the models in production.
Built a recommendation engine for the apparel industry.
Investigated and implemented state-of-the-art models that are able to mimic professional stylists.
Conducted interviews for new ML-related roles and helped during the hiring process.
Implemented and trained several large-scale GAN models.

Technologies: PyTorch, Ubuntu, Artificial Intelligence (AI), Deep Neural Networks, Computer Vision, Deep Learning, Machine Learning, Azure, Python, MySQL, TensorFlow, SQL, Statistical Modeling, Statistics, Data Engineering, APIs, ETL, JSON, Data Science, SQLite, NumPy, Amazon Web Services (AWS), Docker, Kubernetes, Linux, Neural Networks, SciPy, Logistic Regression, Generative Adversarial Networks (GANs), Data Mining, Reinforcement Learning, HTML, Data Analysis, Analysis, Scraping, PyCharm, Image Recognition, Azure SQL, Jupyter, Jupyter Notebook, XML, Unix, Amazon EC2, JavaScript, Image Processing, OpenCV

Machine Learning Engineer

2019 - 2020

Ydrive

Collaborated on building next-generation high-definition maps for autonomous vehicles.
Implemented and designed state-of-the-art models for semantic segmentation, lane detection, depth estimation, and more.
Participated in refactoring a structure from motion (SfM) pipeline.

Technologies: PyTorch, C++, Ubuntu, Artificial Intelligence (AI), Deep Neural Networks, Computer Vision, Machine Learning, Python, TensorFlow, Image Recognition, CMake, Bash, SQL, Statistical Modeling, Statistics, Data Engineering, APIs, ETL, JSON, Data Science, SQLite, NumPy, Amazon Web Services (AWS), Kubernetes, Linux, C, Neural Networks, Recurrent Neural Networks (RNNs), SciPy, Logistic Regression, Data Mining, Reinforcement Learning, Self-driving Cars, HTML, Data Analysis, Analysis, PyCharm, Make, Deep Reinforcement Learning, OpenGL, Azure SQL, XML, Unix, Point Clouds

Senior Software Engineer

2017 - 2019

Lotusflare

Supported several critical back-end components that handle more than two million users daily.
Performed technical interviews for various roles in the company.
Implemented several back-end modules in Lua and OpenResty.

Technologies: C++, Ubuntu, ClickHouse, Redis, Cassandra, Python, Lua, SQL, Statistical Modeling, Statistics, Data Engineering, APIs, ETL, JSON, Data Science, SQLite, NumPy, Amazon Web Services (AWS), Docker, Kubernetes, Linux, Agile, C, Neural Networks, SciPy, Logistic Regression, Apache Kafka, Data Mining, Boost, Kanban, HTML, Data Analysis, Analysis, PyCharm, Make, Qmake, Standard Template Library (STL), XML, Unix, Amazon EC2

Machine Learning Engineer

2017 - 2017

SparcXSoftware (via Toptal)

Implemented a clustering algorithm for extracting significant locations in GPS data collected from the user's phone.
Designed and implemented a model for clothes tagging.
Conducted interviews for machine learning roles and managed two interns.

Technologies: PyTorch, Ubuntu, Artificial Intelligence (AI), Deep Neural Networks, Computer Vision, Deep Learning, Machine Learning, Keras, TensorFlow, Python, SQL, Statistics, Data Engineering, APIs, ETL, JSON, Data Science, SQLite, NumPy, Amazon Web Services (AWS), Docker, Kubernetes, Linux, Neural Networks, SciPy, Logistic Regression, Data Mining, HTML, Data Analysis, Analysis, PyCharm, Image Recognition, Jupyter, Jupyter Notebook, XML, Unix, Amazon EC2, Node.js, JavaScript

Lead Developer

2015 - 2017

Future Gaming Europe

Managed team of four developers and a QA engineer to help develop a casino management system consisting of both hardware and software, with several modules for tracking transactions and cash flow, monitoring players, and tracking staff activity.
Contributed to the development of the C++/Qt application that runs on Raspberry Pi, which is installed into slot machines and provides a user interface for interacting with the system.
Developed several back-end modules, including ticketing and a game called Jackpot.
Conducted interviews and mentored junior developers.

Technologies: C++, Ubuntu, Computer Vision, Machine Learning, PostgreSQL, Raspberry Pi, C#, Qt, SQL, Statistics, Data Engineering, APIs, JSON, Data Science, Raspbian, NumPy, Docker, React, Linux, Windows, Microsoft Visual Studio, Agile, MongoDB, Java, HTML5, Android, C, Neural Networks, Boost, Kanban, HTML, Data Analysis, Analysis, PyCharm, Eclipse IDE, Make, Qmake, Standard Template Library (STL), XML, Unix, Oracle, Visual Studio 2016, Unity

Early-stage Researcher

2015 - 2016

Faculty of Mathematics

Worked on a project called "Predicting patients' future health state" in collaboration with several academic institutions, including the University of Geneva, the University of Maribor, and the Faculty of Mathematics in Belgrade.
Worked on the development and deployment of fast, effective, and interpretable algorithms for healthcare using advanced machine learning techniques, including regularized logistic regression, multi-task learning, and deep learning.
Participated in presenting results and relevant papers.

Technologies: PyTorch, Ubuntu, Artificial Intelligence (AI), Deep Neural Networks, Computer Vision, Deep Learning, Python, TensorFlow, Lua, Torch, MATLAB, SQL, Statistics, Data Engineering, APIs, Data Science, NumPy, Amazon Web Services (AWS), Linux, HTML, Data Analysis, Analysis, PyCharm, XML, Unix

Software Developer

2012 - 2014

PSTech (Acquired by Endava)

Worked on the Cisco Jabber project. Cisco Jabber lets you access presence, instant messaging (IM), voice, video, voice messaging, desktop sharing, and conferencing.
Focused on the contact search engine, a cross-platform component of Jabber.
Contributed to the development of CUCI-Lync, a desktop integration that provides access to Cisco Unified Communications from Microsoft Lync.

Technologies: C++, Ubuntu, C#, SQL, APIs, Data Science, NumPy, Linux, Windows, Microsoft Visual Studio, Kanban, HTML, Data Analysis, Analysis, PyCharm, Standard Template Library (STL), XML, Unix

Experience

Teaching Assistanceship at a Mathematical Gymnasium

Taught algorithms and data structures to bright young mathematicians who have achieved notability in mathematics competitions. The curriculum's focus was helping students gain practical experience in implementing various algorithms in the C# programming language.

Monodepth

I implemented the paper "Unsupervised Monocular Depth Estimation with Left-Right Consistency in TensorFlow." This method presents a novel training objective that enables convolutional neural networks to learn to perform single image depth estimation, despite the absence of ground truth depth data.

Semantic Segmentation

https://github.com/andrijazz/playground/tree/master/projects/fcn

Implementation of the paper "Fully Convolutional Networks for Semantic Segmentation." This implementation shows that convolutional networks by themselves, trained end-to-end and pixels-to-pixels, exceed the state-of-the-art in semantic segmentation.

Newsy

https://github.com/Andrijazz/Newsy

Based on the substantial amount of news articles collected from the web, and using the Bayesian naive approach, "Newsy" classifies a given article into one out of ten different categories (sport.basketball, sport.football, culture, life, politics, etc.).

Technologies used include C++, Qt, Perl, MongoDB, and more.

Smarting

Developed an Android app for acquiring data from a device for a startup company based in Belgrade which is developing a fully mobile, wearable device for recording and analyzing electrical brain activity and wrote drivers for a major software platform dedicated to designing, testing, and using brain-computer interfaces such as OpenVibe and BCI2000.

Technologies used include MATLAB, Python, C++, Java, Android, and more.

Skills

Languages

C++, Lua, Python, SQL, XML, HTML5, JavaScript, HTML, Java, C, C#, Bash

Frameworks

Qt, Boost, Unity

Libraries/APIs

TensorFlow, PyTorch, OpenCV, React, NumPy, SciPy, Node.js, Keras, Standard Template Library (STL), OpenGL, Azure Blob Storage API

Tools

Jupyter, You Only Look Once (YOLO), MATLAB, ChatGPT, PyCharm, Git, Microsoft Visual Studio, Eclipse IDE, Make, Qmake, CMake

Paradigms

Data Science, ETL, Agile, Kanban

Platforms

Amazon EC2, Amazon Web Services (AWS), Unix, Ubuntu, Raspbian, Docker, Apache Kafka, Jupyter Notebook, Kubernetes, Azure, Android, Raspberry Pi, Linux, Windows, Oracle, Visual Studio 2016

Storage

SQLite, PostgreSQL, MySQL, JSON, ClickHouse, Cassandra, Redis, MongoDB, Azure SQL

Other

Deep Reinforcement Learning, Logistic Regression, Neural Networks, Torch, Deep Learning, Machine Learning, Deep Neural Networks, Artificial Intelligence (AI), Reinforcement Learning, Computer Vision, Recurrent Neural Networks (RNNs), Generative Adversarial Networks (GANs), Image Recognition, Statistical Modeling, Statistics, Data Engineering, APIs, Object Detection, Image Processing, Data Mining, Natural Language Processing (NLP), Self-driving Cars, GPT, Generative Pre-trained Transformers (GPT), Open-source LLMs, Generative Artificial Intelligence (GenAI), Data Analysis, Analysis, Scraping, Large Language Models (LLMs), Computer Science, Point Clouds

Education

2012 - 2014

Master's Degree in Computer Science and Mathematics

Faculty of Mathematics, University of Belgrade - Belgrade, Serbia

2005 - 2012

Bachelor's Degree in Computer Science and Mathematics

Faculty of Mathematics, University of Belgrade - Belgrade, Serbia

Certifications

SEPTEMBER 2019 - PRESENT

Sequence Models

Coursera

FEBRUARY 2018 - PRESENT

Machine Learning

Coursera

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.

Share your needs

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

Choose your talent

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

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