Lovro Iliassich, Developer in Rijeka, Croatia
Lovro is available for hire
Hire Lovro

Lovro Iliassich

Verified Expert  in Engineering

Bio

Lovro is a machine learning engineer and data scientist, especially enthusiastic about deep learning applications. Combining his academic knowledge with practical experience in the industry, he can contribute to any part of an AI software development process. Lovro's work experience ranges from startups to corporations—he worked as an engineer at Amazon—and research in academic institutions and universities.

Portfolio

Toptal and Toptal Clients
Amazon Web Services (AWS), Keras, OpenCV, Pandas, Python 3, SQL...
Trust & Safety Laboratory Inc.
Python, Machine Learning, Generative Pre-trained Transformers (GPT)...
Freelance Clients
Data Science, Predictive Modeling, Predictive Analytics, Clinical Trials...

Experience

  • Data Science - 12 years
  • Python - 10 years
  • Machine Learning - 10 years
  • Artificial Intelligence (AI) - 10 years
  • Deep Neural Networks (DNNs) - 7 years
  • Computer Vision - 5 years
  • Natural Language Processing (NLP) - 5 years
  • Generative Pre-trained Transformers (GPT) - 3 years

Availability

Part-time

Preferred Environment

Amazon Web Services (AWS), Python 3, Python

The most amazing...

...research I've developed is a post-doc project at the European Space Agency that uses computer vision for the Mars Lander navigation.

Work Experience

Machine Learning Engineer | Data Scientist | Technical Screener

2017 - PRESENT
Toptal and Toptal Clients
  • Interviewed 500 Toptal candidates as a technical screener for the artificial intelligence and data science specializations.
  • Had two and a half years of experience on NLP projects focusing on language models, social media post analysis, and job/resume matching.
  • Built a computer vision pipeline with a convolutional neural network model for the visual analysis of lab samples.
  • Developed predictive models for disease detection from genomic data (two separate projects).
  • Built predictive models of customer behavior (churn, lifetime, and spending).
  • Developed a convolutional neural network model for sound recognition and classification.
  • Created a computer vision/machine learning service for automatic lab sample assessment.
  • Architected an automated test assessment tool (computer vision, OCR).
Technologies: Amazon Web Services (AWS), Keras, OpenCV, Pandas, Python 3, SQL, Artificial Intelligence (AI), Machine Learning, Algorithms, Scikit-learn, TensorFlow, Python, Computer Vision, Deep Neural Networks (DNNs), Data Science, Natural Language Processing (NLP), Generative Pre-trained Transformers (GPT), Deep Learning, PyTorch, Regression, Regression Modeling, Classification, Neural Networks, Convolutional Neural Networks (CNNs), XGBoost, Visualization, Recommendation Systems, Image Recognition, Predictive Modeling, CatBoost, Language Models, Linux, Optical Character Recognition (OCR), Minimum Viable Product (MVP), Cloud, Data Preprocessing, Feature Analysis, Healthcare, Microsoft Excel, Object-oriented Programming (OOP), Adobe Photoshop, Database Modeling, REST, Jupyter Notebook, APIs, Data Analysis, Statistics, Image Processing, Time Series Analysis, Time Series, Amazon SageMaker, Databricks, Selenium, Google Cloud, REST APIs, PDF, Web Development, ChatGPT, Data Scientist, Data Scraping, Large Language Models (LLMs), Windows, Graphical User Interface (GUI), Agile Software Development, AI Model Training, Algorithm Design, Technical Leadership

Machine Learning Developer

2021 - 2023
Trust & Safety Laboratory Inc.
  • Developed and maintained an NLP model and the pipeline.
  • Processed texts from textual databases and reviews.
  • Developed language models for semantic text comparison.
  • Scraped web articles and social networks for targeted content.
  • Developed a model for detecting targeted content in posts.
Technologies: Python, Machine Learning, Natural Language Processing (NLP), Generative Pre-trained Transformers (GPT), Deep Neural Networks (DNNs), CatBoost, Language Models, Amazon Web Services (AWS), Regression, Regression Modeling, Classification, Neural Networks, XGBoost, Visualization, Deep Learning, PyTorch, Linux, Cloud, Data Preprocessing, Feature Analysis, Jupyter Notebook, Data Analysis, Sentiment Analysis, Data Scientist, Large Language Models (LLMs), Agile Software Development, AI Model Training

Data Scientist

2020 - 2021
Freelance Clients
  • Developed a model for detecting early stages of cancer based on genomic data.
  • Developed a model for detecting chronic kidney disease based on genomic data.
  • Dealt with both small datasets and huge ones using Spark.
Technologies: Data Science, Predictive Modeling, Predictive Analytics, Clinical Trials, Genomics, Classification, Deep Learning, Cloud, Data Preprocessing, Feature Analysis, Jupyter Notebook, Data Analysis, Statistics, Data Scientist, AI Model Training

Software Development Engineer

2017 - 2018
Amazon
  • Developed services for Amazon's global fashion retail program.
  • Set up and deployed services for European markets.
  • Worked with notifications, email services, and templates.
Technologies: Amazon Web Services (AWS), Full-stack, Java, Linux, Cloud, Agile Software Development

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: Pandas, Python 3, Data Science, Java, Artificial Intelligence (AI), Machine Learning, Algorithms, Python, Classification, Visualization, Data Preprocessing, Rankings, Jupyter Notebook, Data Analysis, Data Scientist, Research, AI Model Training, Algorithm Design

Research Engineer

2012 - 2015
INRIA
  • Parallelized machine learning algorithms (SVM, affinity propagation (AP), gradient descent, and more).
  • Conducted high-performance computing low-level optimization. Adapted algorithms for a large-memory (8 TB RAM) NUMA architecture, on a low level (in C/C++), with cache processes' awareness, memory block latencies, and process to the core assignment.
  • Worked on a semantic web project (RDF, Wikidata mining). Implemented a crawler and category recommender system for Wikipedia.
Technologies: Python 3, Data Science, Java, Machine Learning, Algorithms, MATLAB, Python, C, C++, Classification, Visualization, Linux, Distributed Computing, Data Preprocessing, Parallel Computing, Data Analysis, Statistics, Data Scientist, Data Scraping, Research, Algorithm Design

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 the development of the university information system and its business process management workflow.
  • Prepared and published course material for online courses.
Technologies: Java, UML, Web, University Teaching, Web Development, Research

Post-doc Researcher

2010 - 2011
University of Eastern Piedmont
  • Collaborated on a project with the European Space Agency, focusing on the application of computer vision for the Mars Lander navigation.
  • Spearheaded the development of a real-time navigation system using C/C++ and OpenCV. This involved the intricate analysis of live camera feeds from the Mars Lander's lower-mounted camera, tasked with accurately determining the lander's position.
  • Identified and tracked distinctive features within the video stream, integrating data from other vital sensors such as lidar and inertial measurement units.
  • Modeled the Martian surface in Java 3D, simulating lighting to mimic various times of the day.
  • Built a Mars Lander landing simulator in C/C++ and MATLAB.
Technologies: OpenCV, Java, Artificial Intelligence (AI), Machine Learning, Algorithms, MATLAB, C, C++, Computer Vision, Visualization, Image Recognition, Statistics, Image Processing, Data Scientist, Research, Algorithm Design

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 the usage of a grid computing network.
  • Contributed to fields of graph analysis and complex systems analysis.
Technologies: Data Science, Java, Machine Learning, Algorithms, Predictive Modeling, Grid Computing, Statistics, Time Series Analysis, Research

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 models to database design, back-end business logic, front end, web (including web design), and stand-alone clients.
  • Designed, architected, and implemented a government information system, fleet management system, and more.
Technologies: Full-stack, SQL, Java, UML, HTML, Web, Databases, Healthcare, Object-oriented Programming (OOP), Adobe Photoshop, Database Modeling, REST, Web Development, Windows, Graphical User Interface (GUI)

Experience

Ranked Data Analysis

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

It Snows

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

https://github.com/lovro-i/apro
A parallelized Java implementation of the affinity propagation clustering algorithm.

Mandrago

A personal startup project of mine—a mobile workforce and dispatching system. I served as a co-owner, architect, designer, and developer. I implemented the whole stack, from the infrastructure, back end, web front end, and mobile front end.

Heliant HIS

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

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

Skidea

http://skidea.com
My own startup project—Ski resort maps on Garmin GPS devices. I collected and processed OpenStreetMaps geospatial data to create custom Garmin ski maps. I implemented a web interface and back end, offering free and paid versions of ski resort maps.

Mountain Rescue Service Information System

http://rescue.gss.rs
I worked on the architecture and development of the Mountain Rescue Service information system, including the workflow of mountain rescuers and ski patrollers: HRMS, shifts, rescue missions, and reports. I built the back end in AWS using lambda functions, API Gateway, DynamoDB, and Cognito. I developed the front end in React.

Sailweek Staff

http://sailweek.com
Sailweek is a company that organizes weekly yachting tours with 20–50 sailboats in a fleet. This requires managing skippers, hostesses, and boats.

I worked on the architecture and development of the company's information system, which included the workflow of skippers and hostesses: HRMS, assigning boats, and reports. I built the back end in AWS using lambda functions, API Gateway, DynamoDB, and Cognito. I developed the front end in React.

TaxBot: RAG-based Chatbot

Developed a retrieval-augmented generation (RAG) chatbot to assist with tax-related inquiries for a national tax service. I architected and implemented the entire system, leveraging a serverless framework for the back end (AWS API Gateway, DynamoDB, Lambda), Qdrant for vector database management, and React for the front end. I integrated OpenAI's ChatGPT API to provide intelligent and context-aware responses. My responsibilities included end-to-end development, from designing the architecture to deploying a fully operational solution.

Education

2006 - 2010

Ph.D. in Computer Science

University of Turin, Department of Informatics - Turin, Italy

2001 - 2004

Master of Science Degree in Computer Systems and Networks

University of Belgrade, School of Electrical Engineering - Belgrade, Serbia

1995 - 2001

Bachelor of Science Degree in Computer Science and Technology

University of Belgrade, School of Electrical Engineering - Belgrade, Serbia

Skills

Libraries/APIs

REST APIs, Scikit-learn, TensorFlow, PyTorch, Keras, OpenCV, XGBoost, Pandas, NumPy, Matplotlib, LSTM, Google API, React, Spark ML, jQuery, PySpark, Google Maps API, PayPal API, CatBoost, Stripe API, Stripe, OpenAI API

Tools

Jupyter, Adobe Photoshop, Algorithm Design, Amazon Simple Queue Service (SQS), ChatGPT, Microsoft Excel, You Only Look Once (YOLO), Amazon SageMaker, MATLAB, Trello, Amazon Cognito, Amazon Simple Notification Service (SNS), OpenAI Gym

Languages

Python, Java, SQL, Python 3, CSS, HTML5, HTML, UML, C++, JavaScript, C

Paradigms

RESTful Development, Parallel Computing, REST, Model View Controller (MVC), Object-oriented Programming (OOP), Functional Programming, ETL, Distributed Computing, High-performance Computing (HPC), Distributed Programming, Agile Software Development, Test-driven Development (TDD), Kanban, Real-time Systems

Platforms

Jupyter Notebook, Amazon Web Services (AWS), Amazon EC2, Android, Linux, Windows, Web, Databricks, Google Cloud Platform (GCP), AWS Lambda, Docker

Storage

Database Modeling, Amazon S3 (AWS S3), PostgreSQL, MySQL, Amazon DynamoDB, Google Cloud, Databases

Frameworks

Android SDK, Play Framework, Selenium, JUnit, Apache Spark, Spark, Streamlit, Serverless Framework

Industry Expertise

Healthcare

Other

Algorithms, Recurrent Neural Networks (RNNs), Unsupervised Learning, Clustering Algorithms, Clustering, Regression Modeling, Regression, Classification Algorithms, Classification, Deep Neural Networks (DNNs), Deep Learning, Convolutional Neural Networks (CNNs), Neural Networks, Computer Vision, Machine Learning, Data Mining, Data Modeling, Data Science, Scientific Computing, Data Visualization, Artificial Intelligence (AI), Natural Language Processing (NLP), Web Development, Software Architecture, Back-end, Data Scientist, Generative Pre-trained Transformers (GPT), Data Preprocessing, Feature Analysis, OpenAI GPT-3 API, OpenAI GPT-4 API, Chatbots, Prompt Engineering, K-means Clustering, AI Chatbots, Forecasting, Long Short-term Memory (LSTM), LSTM Networks, AI Model Training, APIs, Full-stack, Data Architecture, Cloud, Recommendation Systems, Image Recognition, Predictive Modeling, Sentiment Analysis, Geospatial Data, Cloud Platforms, Graphical Models, Image Processing, Data Analysis, Time Series, Time Series Analysis, Data Analytics, Data Reporting, Statistics, Visualization, University Teaching, Minimum Viable Product (MVP), BERT, Data Scraping, Distributed Systems, Natural Language Queries, Large Language Models (LLMs), Spanish, Research, Graphical User Interface (GUI), OpenAI, Hierarchical Clustering, Optimization, Mathematics, Retrieval-augmented Generation (RAG), Statistical Analysis, Architecture, Generative Artificial Intelligence (GenAI), Technical Leadership, Web Crawlers, Big Data, Serverless, Data Engineering, OpenStreetMap, Stochastic Modeling, Web Scraping, Signal Processing, Robot Operating System (ROS), Reinforcement Learning, Generative Adversarial Networks (GANs), Web MVC, Mapping, Language Models, Optical Character Recognition (OCR), Amazon API Gateway, PDF, A/B Testing, Predictive Analytics, Clinical Trials, Genomics, Computer Networking, Software Engineering, Monitoring, Electrical Engineering, Digital Electronics, Computer Science, Rankings, Grid Computing, LangChain, DBSCAN, Hugging Face, Deep Reinforcement Learning, Qdrant, ChatGPT API, Vector Databases, Machine Learning Operations (MLOps)

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