Lovro Iliassich, Machine Learning Developer in Rijeka, Croatia
Lovro Iliassich

Machine Learning Developer in Rijeka, Croatia

Member since January 7, 2016
Lovro is a machine learning engineer and a data scientist, especially enthusiastic about neural network applications. Combining his academic knowledge with practical experience in the industry, he can contribute to any part of an AI software development process. He worked as an engineer at Amazon as well as a researcher at several universities and institutes.
Lovro is now available for hire

Portfolio

Experience

Location

Rijeka, Croatia

Availability

Full-time

Preferred Environment

Windows, Linux, AWS

The most amazing...

... engagement I've had is a post-doc project at the European Space Agency on using computer vision for navigation of the Mars Lander.

Employment

  • Machine Learning Engineer, Data Scientist, and Technical Screener

    2017 - PRESENT
    Toptal and Toptal Clients
    • Interviewed more than 200 Toptal candidates as a technical screener for artificial intelligence and data science specializations.
    • Developed a convolutional neural network model for sound recognition and classification.
    • Developed a neural network model for visual analysis of lab samples.
    • Created predictive modeling of chronic diseases from genomic data using Spark.
    • Developed predictive models of customer behavior (churn, lifetime, and spending).
    Technologies: Python, TensorFlow, Scikit-learn, OpenCV
  • Software Development Engineer

    2017 - 2018
    Amazon
    • Developed services for global fashion retail.
    Technologies: Java
  • Research Scholar

    2015 - 2016
    Drexel University
    • Brought in as a visiting scholar at the Department of Computer Science, Database Group.
    • Researched mining and modeling rank and preference data.
    • Implemented a Java library for handling and mining rank and preference data.
    • Published papers on novel approaches to model user preferences.
    Technologies: Java, Python, Machine Learning
  • Research Engineer

    2012 - 2015
    INRIA
    • Parallelized machine learning algorithms (SVM, affinity propagation, neural networks, etc.).
    • Conducted high-performance computing on low level. Adapted algorithms for a large-memory (8 TB RAM) NUMA architecture, on a low level (in C/C++), with the awareness of cache processes, memory blocks latencies, and exact control over the assignment of threads to cores.
    • Worked on a semantic web project (RDF, Wikidata mining). Implemented a crawler and category recommender system for Wikipedia.
    • Managed big data and ETL processes.
    Technologies: Java, C/C++, Python, MATLAB
  • Assistant Professor

    2011 - 2012
    Metropolitan University
    • Taught at the undergraduate and graduate level, including courses in web systems and applications, distributed systems, and information system design.
    • Worked on development of the university information system and its business process management workflow.
    Technologies: Java, Web, UML
  • Post-doc Researcher

    2010 - 2011
    University of Eastern Piedmont
    • Worked on a European Space Agency project on using computer vision for Mars Lander navigation.
    • Implemented a real-time navigation system in C/C++ with OpenCV. Analyzed the image stream from the camera attached to the bottom of Mars Lander with the task of calculating the position of the lander (coordinates, altitude, attitudes).
    • Tracked features in the video. Filtered the output and combined information with other sensors (lidar, inertial measurement unit).
    • Modeled the Mars surface in Java 3D.
    • Built a Mars Lander landing simulator in C/C++ and MATLAB.
    Technologies: Java, C/C++, MATLAB
  • Ph.D. Student

    2006 - 2010
    University of Turin, Department of Computer Science
    • Completed doctoral studies in the field of data mining and machine learning.
    • Performed text mining and document classification on local government data (NLP).
    • Researched sequential pattern mining; recognizing users by keyboard strokes.
    • Developed a log mining model for predicting usage of a grid computing network.
    • Contributed to fields of graph analysis and complex systems analysis.
    Technologies: Java, Weka
  • Software Engineer

    2001 - 2006
    RCUB
    • Designed and architected a wide area network monitoring system, used in several huge organizations and companies (banks and telecommunications).
    • Designed, implemented, and led the team of the hospital information system currently in use in about 75% of the hospitals in Serbia.
    • Gained experience in all aspects of the implementation of large information systems, from interviews, specifications, and UML model to database design, back-end business logic, front end, web (including web design), and stand-alone clients.
    • Worked on a government information system, fleet management system, and more.
    Technologies: Java, Web stack, UML

Experience

  • Ranked Data Analysis (Development)

    Mining and modeling ranked (preference) data. The research project resulted in new methods of using partial user preferences for modeling user population.

  • It Snows (Development)

    A personal pet project: a ski community mobile application. I built the server back end and web services and implemented an Android mobile application as a front end.

  • Java Affinity Propagation Library (Development)
    https://github.com/lovro-i/apro

    A parallelized Java implementation of the affinity propagation clustering algorithm.

  • Mandrago (Development)
    http://mandrago.com

    A mobile workforce and dispatching system, a personal startup project. Co-owner and developer.

  • Heliant HIS (Development)

    I architected and designed the hospital information system used currently by about three quarters of the hospitals and clinics in Serbia. The system covers the hospital workflow, scheduling, medical records, etc.

  • Network Monitoring System (Development)

    A wide-area network monitoring system. Used by the Academic Network of Serbia, National Bank, and a couple of banks and telecommunications companies.

  • Skidea (Development)
    http://skidea.com

    Collection of ski resort maps for Garmin GPS devices.

  • Clustering Algorithms: From Start To State Of The Art (Publication)
    Clustering algorithms are very important to unsupervised learning and are key elements of machine learning in general. These algorithms give meaning to data that are not labelled and help find structure in chaos. But not all clustering algorithms are created equal; each has its own pros and cons. In this article, Toptal Freelance Software Engineer Lovro Iliassich explores a heap of clustering algorithms, from the well known K-Means algorithm to the elegant, state-of-the-art Affinity Propagation technique.

Skills

  • Languages

    Python, Java, SQL, Python 3, CSS, HTML5, HTML, UML, C++, JavaScript, C
  • Libraries/APIs

    Scikit-learn, TensorFlow, Keras, OpenCV, XGBoost, Pandas, NumPy, PyTorch, Google API, Spark ML, jQuery, PySpark, Google Maps API
  • Tools

    Jupyter, Adobe Photoshop, Amazon SageMaker, Weka, MATLAB, Trello
  • Paradigms

    Parallel & Distributed Computing, REST, Model View Controller (MVC), Data Science, Object-oriented Programming (OOP), Functional Programming, ETL, High-performance Computing, Distributed Programming, Test-driven Development (TDD), Kanban
  • Platforms

    Jupyter Notebook, Amazon Web Services (AWS), AWS EC2, Android, Linux, AWS Lambda, Docker
  • Storage

    Database Modeling, AWS S3, PostgreSQL, MySQL, AWS DynamoDB
  • Other

    Algorithms, Recurrent Neural Networks, RESTful APIs, Unsupervised Learning, Clustering Algorithms, Clustering, Regression Models, Regression, Classification Algorithms, Classification, Deep Neural Networks, Deep Learning, Convolutional Neural Networks, Neural Networks, Computer Vision, Machine Learning, Data Mining, Data Modeling, Scientific Computing, Data Visualization, Artificial Intelligence (AI), Natural Language Processing (NLP), APIs, Full-stack, Data Architecture, Recommendation Systems, Image Recognition, Predictive Modeling, Graphical Models, Image Processing, AWS, Data Analysis, Time Series, Time Series Analysis, Data Analytics, Data Reporting, Statistics, Visualization, Web Crawlers, Cloud, Big Data, Serverless, Signal Processing, ROS, Reinforcement Learning, Generative Adversarial Networks (GANs)
  • Frameworks

    Android SDK, Play Framework, JUnit, Apache Spark, Spark

Education

  • Ph.D. in Computer Science
    2006 - 2010
    University of Turin, Department of Informatics - Turin, Italy
  • Master of Science degree in Computer Systems and Networks
    2001 - 2004
    University of Belgrade, School of Electrical Engineering - Belgrade, Serbia
  • Bachelor of Science degree in Computer Science and Technology
    1995 - 2001
    University of Belgrade, School of Electrical Engineering - Belgrade, Serbia

To view more profiles

Join Toptal
Share it with others