Drazen Zaric, Developer in Belgrade, Serbia
Drazen is available for hire
Hire Drazen

Drazen Zaric

Verified Expert  in Engineering

Bio

Drazen is a data scientist and data engineer with over seven years of experience building analytics infrastructure, machine learning, and data analysis. He has extensive experience in big data, machine learning, and web development. He has worked with notable companies such as Slack and Microsoft, and built products used by millions of users.

Portfolio

Delivery Hero
PyTorch, Graphs, Graph Neural Networks, Neural Networks, Deep Learning...
Property Guard
Python, Python 3, DigitalOcean, Scraping, Redis Queue, Message Queues, Docker...
Teespring
Tableau, Data Visualization, Data Science, Python, Redshift, Snowflake...

Experience

  • Data Science - 10 years
  • Python - 8 years
  • Deep Learning - 4 years
  • Natural Language Processing (NLP) - 4 years
  • Machine Learning - 4 years
  • Large Language Models (LLMs) - 2 years

Availability

Part-time

Preferred Environment

Vim Text Editor, Python, Linux, MacOS

The most amazing...

...project I've built was an analytics infrastructure for a product with 150 million users.

Work Experience

Senior Data Scientist

2022 - 2024
Delivery Hero
  • Led the effort to optimize the processing and storage of a large-scale customer network graph. Reduced costs by 10x and feature calculation latency by 120x.
  • Developed a graph neural network model for courier fraud.
  • Developed and maintained fraud models for payment and refund fraud. Improved a cash payment risk model to 3x its financial value.
Technologies: PyTorch, Graphs, Graph Neural Networks, Neural Networks, Deep Learning, LightGBM, Machine Learning, Fintech, Fraud Detection, Scikit-learn

Senior Python Developer

2021 - 2022
Property Guard
  • Developed a scalable, distributed web crawler using Python, Flask, Redis on DigitalOcean cloud.
  • Created an autoscaling system leveraging DigitalOcean Droplets and Docker.
  • Developed and tested several components of the distributed system, including the orchestrator service, Redis queue, ELK monitoring, and DigitalOcean and Ansible infrastructure provisioning.
Technologies: Python, Python 3, DigitalOcean, Scraping, Redis Queue, Message Queues, Docker, Elasticsearch, PostgreSQL

Data Scientist

2019 - 2020
Teespring
  • Collaborated as a part of the data team. Developed dashboards in Tableau and data reports with Redash; worked on migrating from Redshift to Snowflake.
  • Supported the commercial and partnership teams with data insights.
  • Developed an interactive real-time map visualization of Teespring sales with JavaScript and Mapbox.
Technologies: Tableau, Data Visualization, Data Science, Python, Redshift, Snowflake, Data Analysis, MySQL, ETL, APIs, Dashboard Design, Dashboards, Interactive Maps, SQL, Big Data, Data Modeling, Database Modeling

Analytics Consultant

2019 - 2019
Freelance Consultant
  • Collaborated with small companies on establishing their data infrastructure, discipline, and teams.
  • Assessed existing processes, available data, and infrastructure.
  • Planned for future growth in terms of product and the team.
  • Helped with descriptive and predictive user behavior models, segmentation, and A/B testing.
Technologies: Tableau, Big Data, SQL

Product Manager

2017 - 2018
Nordeus
  • Led the team in developing Golden Boot, a game for a then-new platform called Facebook Instant Games. This product grew from an idea to over 10 million players in four months.
  • Oversaw product and project management, back-end development, data analysis, and game design within an Agile team.
  • Developed high-performance algorithms for matchmaking.
  • Created a distributed push notifications system backed by a Hadoop data warehouse and a machine learning model for user churn.
Technologies: Apache Impala, Hadoop, Aerospike, JavaScript, Python, Java, Product Management, App Product Management, Development, Agile, Scrum, Data Analysis, Lean Project Management

Data Scientist

2015 - 2017
Nordeus
  • Developed internal data products. Designed, developed, and deployed optimization algorithms for in-game tournament generation.
  • Created machine learning models for anomaly detection, product performance, and user behavior prediction tools for optimizing marketing campaigns.
  • Maintained and improved a custom, in-house BI tool.
  • Supported product managers, game designers, and user acquisition teams with analyses and insights.
Technologies: Pandas, NumPy, Scikit-learn, Flask, Tableau, SQL, Machine Learning, Python, Data Analysis, Databases, Database Analytics, PostgreSQL, Apache Impala, Data Visualization, Dashboard Design, Agile, Git, MySQL, Hadoop

Data Engineer

2013 - 2015
Nordeus
  • Developed and maintained an in-house ETL system and data warehouse on top of Hadoop and Impala for TopEleven, an online game with over 150 million players.
  • Transitioned a single PostgreSQL instance to an in-house Hadoop cluster solution.
  • Designed and wrote data import, SQL transformations, and oversaw the data quality.
  • Integrated data from internal and third-party data sources.
  • Scaled data warehouse and processes from a single product to multiple products.
Technologies: Hadoop, SQL, Python, Data Engineering, Apache Impala, PostgreSQL, MySQL, Data Analytics, Data Analysis, Linux, Bash, Git, Back-end, Databases, ETL, ETL Tools, ETL Testing, ETL Development, Data Modeling, Database Modeling

Software Development Engineer

2011 - 2013
Microsoft
  • Developed the PDF Reflow feature for Microsoft Word 2013.
  • Designed algorithms for converting a PDF into an editable DOCX document.
  • Implemented and evaluated machine learning models for identifying parts of a PDF document.
Technologies: C++, Algorithms, Software Engineering, Agile, Scrum

Experience

Blogboard

https://blogboard.io
Blogboard is a search and discovery engine for official blogs of leading tech companies.

As a solo creator, I worked on the front-end development in Vue and the back end and search in Python, PostgreSQL, and Elasticsearch. I also wrote the official product blog.

Top Eleven by Nordeus

https://www.topeleven.com/
A highly successful online sports game, Top Eleven, has had over 150 million players to date. I worked on the analytics infrastructure, product management, data science, and in-game algorithm development.

Upvote for Slack

https://upvote.chat
Upvote is a Slack-native polling app that gives you a smooth experience with visually appealing polls.

Upvote is a small, profitable product. I developed the app end-to-end, including the back end, front end, Slack API integration, UX and UI design, and marketing.

Selecta: An Amarok Player Extension

https://github.com/drazenz/Selecta
This is an inverted index and TF-IDF retrieval engine for music in your library based on last.fm tags. Selecta was implemented from scratch in JavaScript back in the days before music streaming, when music was offline.

Improved Heatmaps in Python

https://github.com/drazenz/heatmap
This is a Python code and a Jupyter notebook for an improved heatmap implementation using Matplotlib and Seaborn.

Similar to what you can easily get in Tableau using a size parameter, here you can have a square as a parameter depending on the field value.

Described in detail in this blog post: https://towardsdatascience.com/better-heatmaps-and-correlation-matrix-plots-in-python-41445d0f2bec

Education

2010 - 2011

Master's Degree of Science in Computer Science

University of Novi Sad - Novi Sad, Serbia

2006 - 2010

Bachelor's Degree in Computer Science

University of Novi Sad - Novi Sad, Serbia

Certifications

JANUARY 2019 - PRESENT

Product Management Program

UC Berkeley Executive Education

Skills

Libraries/APIs

Scikit-learn, Pandas, NumPy, Vue, PyTorch, Redis Queue, Scikit-optimize, SciPy

Tools

Apache Impala, Tableau, Git, Ansible, Vim Text Editor, GitHub

Languages

Python, SQL, C++, JavaScript, Snowflake, Java, Bash, Python 3

Frameworks

Flask, Hadoop, LightGBM

Platforms

Linux, MacOS, Apache Kafka, Web, DigitalOcean, Docker

Storage

PostgreSQL, Aerospike, Redshift, Elasticsearch, MySQL, Databases, Database Modeling

Paradigms

Agile, Scrum, ETL

Other

Data Engineering, Data Science, Machine Learning, Algorithms, Data Analysis, Database Analytics, Neural Networks, Deep Learning, Natural Language Processing (NLP), Data Visualization, Web Development, Optimization, eCommerce, Large Language Models (LLMs), Big Data, Front-end, Back-end, Writing & Editing, Software Engineering, Data Analytics, Dashboard Design, Product Management, App Product Management, Development, Lean Project Management, ETL Tools, ETL Testing, ETL Development, APIs, Dashboards, Interactive Maps, Data Modeling, Scraping, User Experience (UX), User Interface (UI), Data Scraping, Web Scraping, Graphs, Graph Neural Networks, Fintech, Fraud Detection, Message Queues, App UX, Innovation, B2C Marketing, Electrical Engineering, Hardware Design, SEO Tools, Content Writing, Technical Writing, Information Retrieval, Music Information Retrieval (MIR), Open Source, Value Innovation

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