Aleksandar Loncar, Image Recognition Developer in Novi Sad, Vojvodina, Serbia
Aleksandar Loncar

Image Recognition Developer in Novi Sad, Vojvodina, Serbia

Member since June 21, 2019
Aleksandar is a passionate and highly skilled machine learning engineer with a strong background in software engineering and deep expertise in data science, particularly in the areas of deep learning and AI. He has a keen analytical mind and a talent for solving complex and challenging problems.
Aleksandar is now available for hire

Portfolio

Experience

Location

Novi Sad, Vojvodina, Serbia

Availability

Full-time

Preferred Environment

Git, Linux, Windows, MacOS, Jupyter

The most amazing...

...project I've fulfilled is creating new or adjusting algorithms for non-trivial problems.

Employment

  • AI Expert

    2022 - 2022
    Displace Inc
    • Conducted thorough research and found effective hardware and software solutions for the task.
    • Developed custom classifiers and scene reasoning models for lidar sensors.
    • Developed a hand gesture recognition system using pre-trained key-point detection models.
    Technologies: Artificial Intelligence (AI), Computer Vision, Neural Networks, Point Clouds, Artificial Neural Networks (ANN), LiDAR, Deep Learning
  • AI/ML Developer

    2022 - 2022
    Mombe Genetic Investment
    • Designed and trained several highly effective models for recognizing channel patterns in trading data for a stock analysis tool.
    • Designed and developed a few NT8 custom tools for this purpose.
    • Designed a user-friendly and intuitive server-client architecture for the deployment of those models.
    Technologies: Artificial Intelligence (AI), Python, TensorFlow, Machine Learning, Data Analytics, C#
  • Machine Learning Engineer

    2021 - 2022
    DIG Labs Corporation
    • Conducted a thorough and comprehensive data analysis using machine learning and PyTorch for a healthtech startup.
    • Created several advanced computer vision and machine learning models for classifying health-related data, achieving high levels of accuracy and precision.
    • Created a custom framework for streamlining hypothesis cycles and model deployment, enabling faster and more effective experimentation.
    Technologies: PyTorch, Machine Learning, Computer Vision, Deep Learning, TensorFlow, Amazon SageMaker, Data Engineering, Data Science, Python, Artificial Intelligence (AI)
  • AI Developer

    2021 - 2022
    Vous Music Group
    • Acted as an AI developer for a crypto-based project. Developed a blueprint for incorporating machine learning models into the system, taking into account technical, business, and strategic factors.
    • Developed a comprehensive plan for incorporating machine learning into a system of guilds in play-to-earn games, enabling more strategic and dynamic gameplay.
    • Created a ranking system for multiple NFT collections.
    Technologies: Artificial Intelligence (AI), AI Design, Python, Machine Learning, System Design
  • Python Software Developer for 3D Algorithm Project

    2021 - 2021
    Radical Solutions, Inc.
    • Conducted a comprehensive analysis of time series data from bone and joint movements, uncovering key trends and patterns.
    • Used a combination of research and experimentation to tackle this difficult issue.
    • Created a robust and scalable rule-based classifier for body pose analysis using 3D skeleton data.
    Technologies: Python, Software Development, 3D, Prototyping, Data Analysis, 3D Geometric Analysis
  • Data Scientist | Quant Researcher

    2021 - 2021
    TickUp
    • Created models for forecasting time series, performed research on machine learning approaches in the field, time-series trend changes analysis and modeling, and more.
    • Analyzed several data, performed data quality checks, and cleaned pipelines.
    • Operated on datasets provided by Bloomberg and similar providers.
    Technologies: Python, Data Science, Machine Learning, Forecasting, Time Series Analysis, Data Analysis
  • Machine Learning Engineer

    2021 - 2021
    Symphony
    • Developed a machine learning solution that can find forest edges from satellite imagery.
    • Worked as a machine learning engineer on this project, responsible for the R&D process. Analyzed data sources and organized training and inference pipelines for machine learning models in cloud environments.
    • Delivered state-of-the-art solution for the selected computer vision problems.
    Technologies: Computer Vision, Image Recognition, AWS, Amazon SageMaker, Keras, TensorFlow, Python, Jupyter, Machine Learning
  • Machine Learning Engineer

    2020 - 2021
    Symphony
    • Developed a machine learning solution that can estimate building roof attributes (predominant pitch, eave height, story count) from (synthetic) point cloud data and areal imagery.
    • Worked as a team lead and machine learning engineer on this project, responsible for the R&D process.
    • Analyzed data sources and applied classical algorithms from computer vision and Point cloud domains, and machine learning algorithms.
    • Conducted experiments to find the best fitting ML solutions for ML classification and regression models. He also experimented with custom loss functions and data pre-processing based on recent papers.
    Technologies: Amazon SageMaker, Machine Learning, Computer Vision, Image Recognition, AWS, Python, Jupyter, Keras, TensorFlow, Point Clouds
  • Data Scientist | Full-stack Developer

    2020 - 2021
    Atturo
    • Created a system that forecasts future sales based on historical data—time series analysis. The system is used for internal purposes.
    • Developed a web application that allows users to upload historical data (sale data, inventory data, and more), list top-selling items, view trends per warehouse, and make forecasts for future periods.
    • Built a system that optimizes warehouse management.
    Technologies: Data Science, Python, AWS, Flask, Time Series, Sales Forecasting, Time Series Analysis
  • Machine Learning Engineer | Computer Vision

    2020 - 2020
    Faculty of Transportation Sciences (via Toptal)
    • Developed a PoC drone traffic analysis based on computer vision and deep learning algorithms.
    • Researched SotA approaches (papers and solutions) for object detection and object tracking based on video from an aerial perspective: Surveillance cameras, drones/planes, and satellites.
    • Found suitable train datasets for the use case and trained object detectors in AWS cloud.
    Technologies: Machine Learning, AWS, Amazon SageMaker, Computer Vision, TensorFlow, PyTorch, Python, Deep Learning, Image Recognition
  • Computer Vision R&D Engineer | Team Leader

    2019 - 2020
    Ottometric
    • Developed computer vision and deep learning algorithms.
    • Led the analytics team. Worked on computer vision and ML/data science solutions for ADAS (advanced driver assist systems) validation and analyzed terabytes of test drive data.
    • Scaled up ML and other software solutions in the cloud environment(s).
    Technologies: Google Cloud Platform (GCP), Keras, TensorFlow, Python, Machine Learning, Data Science, Artificial Intelligence (AI)
  • Senior Software Engineer, Machine Learning Engineer

    2015 - 2019
    USoft
    • Developed full-stack machine learning pipelines for both a training and production environment in Python.
    • Involved in the development of a face recognition system based on deep learning: A machine learning project developed on the TensorFlow framework.
    • Developed a machine learning model based on transfer learning for leaf counting (plant phenotyping).
    • Developed many regression and classification models for tabular data.
    • Maintained, optimized, and developed some features in a voice authentication system. Responsible for the SIP proxy app that bridges incompatibility between the PBX and their SIP stack.
    Technologies: Redis, .NET, C++, Keras, TensorFlow, C#, Python, Azure, Data Science, Machine Learning, Computer Vision
  • Data Scientist

    2017 - 2018
    Brisqq LTD
    • Performed time series analysis and forecasting.
    • Participated in courier tiers optimization.
    • Developed model for next delivery prediction, time and geo-location. Part of the recommendation system for couriers.
    • Performed geo-location clustering based on data history.
    • Made a model that classifies couriers based on their performances.
    Technologies: MongoDB, Keras, TensorFlow, Python
  • Senior Software Developer, Development Team Leader

    2014 - 2015
    Danulabs
    • Tasked with making enterprise cloud-based software solutions for medical practices and other entities in the domain of healthcare.
    • Developed enterprise software architectures with multi-tenant database models.
    • Led a team of 6+ members, coordinated between UI/UX designers, front-end and back-end devs, and other participants.
    Technologies: Elasticsearch, MySQL, Microsoft SQL Server, Angular, ASP.NET
  • Software Developer

    2012 - 2014
    Danulabs
    • Developed custom web applications.
    Technologies: MySQL, Microsoft SQL Server, C#, ASP.NET

Experience

  • Couriers Delivery Forecasting System

    A recommendation system for couriers based on machine learning models that can predict the next delivery in spatial grid and time, based on historical data.

  • Face Recognition System

    Face Recognition system is a PoC based on deep learning. Users can create profiles on the system, the number of required images for the profile can vary and depend on configuration. Next step is that the user can verify new image against the enrolled profile. The system is set to minimize false positive rate, and prevent impostors to verify as registered users. It can also execute identification against all enrolled users.

    Because it is trained on best-known datasets, it is very robust to illuminance, image blur, head pose variation, gender, and ethnicity.

  • Warehouse Sales Forecasting System

    A Python-based web application for warehouse management optimization.
    I was a full-stack developer and a data scientist. The core of the system is a machine learning model that forecasts sales per warehouse, it consumes historical sales and inventory levels data. The app has rich data visualizations (graphs and trends) and role-based access control, deployed in AWS.

Skills

  • Languages

    Python, C#, C++
  • Libraries/APIs

    Keras, PyTorch, TensorFlow, Pandas
  • Tools

    Amazon SageMaker, Jupyter, Git
  • Paradigms

    Data Science
  • Other

    Artificial Intelligence (AI), Amazon Machine Learning, Google Cloud Machine Learning, Image Recognition, Time Series, Time Series Analysis, Machine Learning, Deep Learning, Computer Vision, Forecasting, Data Analysis, AWS, Sales Forecasting, Point Clouds, Software Development, 3D, Prototyping, 3D Geometric Analysis, AI Design, System Design, Data Engineering, Data Analytics, Neural Networks, Artificial Neural Networks (ANN), LiDAR
  • Storage

    MySQL, Redis, Microsoft SQL Server, Elasticsearch, MongoDB
  • Frameworks

    ASP.NET, Angular, .NET, Flask
  • Platforms

    Windows, Linux, Google Cloud Platform (GCP), Azure, MacOS, Docker

Education

  • Master's Degree in Computer Science
    2012 - 2014
    University of Novi Sad - Novi Sad, Serbia
  • Bachelor's Degree in Computer Science
    2007 - 2011
    University of Novi Sad - Novi Sad, Serbia

Certifications

  • Deep Learning Specialization
    FEBRUARY 2018 - PRESENT
    Coursera
  • Convolutional Neural Networks
    FEBRUARY 2018 - PRESENT
    Coursera
  • Sequence Models
    FEBRUARY 2018 - PRESENT
    Corsera
  • Neural Networks and Deep Learning
    AUGUST 2017 - PRESENT
    Coursera
  • Structuring Machine Learning Projects
    AUGUST 2017 - PRESENT
    Coursera
  • Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization
    AUGUST 2017 - PRESENT
    Coursera

To view more profiles

Join Toptal
Share it with others