Leon Coert, Developer in Giessen, Hesse, Germany
Leon is available for hire
Hire Leon

Leon Coert

Verified Expert  in Engineering

Machine Learning Developer

Location
Giessen, Hesse, Germany
Toptal Member Since
September 7, 2020

Leon is a machine learning expert with industry experience creating classification systems and predictive solutions for business applications. He is well-versed in developing complex solutions and possesses strong creative thinking skills. His determination to explore unknown domains in depth makes him an exceptional engineer. Leon's excellent communication and prior experience working on a variety of projects in the artificial intelligence domain help clients achieve their goals.

Portfolio

Toptal
Kubernetes, Apache Airflow, Vertex, Google Cloud Platform (GCP), AWS CLI...
Self-employed
Machine Learning, Generative Pre-trained Transformers (GPT)...
Self-employed
NumPy, Principal Component Analysis (PCA), MySQL, Kibana, Python, PyTorch

Experience

Availability

Part-time

Preferred Environment

Jupyter Notebook, Visual Studio Code (VS Code), Git, Ubuntu

The most amazing...

...project I've implemented was an NLP classification system that reduced operational costs by 80% and helped the company to expand its business internationally.

Work Experience

Senior AI Engineer

2021 - 2023
Toptal
  • Architected and deployed a real-time anomaly detection system for financial transactions, reducing false positive alerts by 80% and improving the efficiency of incident response.
  • Optimized the training pipeline by implementing distributed computing techniques, reducing model training time by 50% and enabling faster experimentation and iteration.
  • Collaborated with cross-functional teams to integrate machine learning models into production systems, resulting in a 25% increase in operational efficiency and cost savings.
Technologies: Kubernetes, Apache Airflow, Vertex, Google Cloud Platform (GCP), AWS CLI, Convolutional Neural Networks (CNN), Artificial Intelligence (AI), Image Recognition

Artificial Intelligence Engineer

2020 - 2021
Self-employed
  • Solved actual business problems in various domains by utilizing cutting-edge NLP technology like BERT, fastText, PyTorch, spacy, Hugging Face, etc.
  • Ensured that APIs and models were performant and robust in a production environment. Docker, Kubernetes, and cloud technologies were used to ensure scalability and reproductivity in the production environment.
  • Contributed to applications ranging from sentence classification and sentiment analysis to fraud detection in financial transaction data.
  • Built and deployed a highly scalable ML pipeline to categorize financial transaction data in real-time.
Technologies: Machine Learning, GPT, Generative Pre-trained Transformers (GPT), Natural Language Processing (NLP), MySQL, Kibana, PyTorch, Scikit-learn, Python, Computer Vision

Machine Learning Engineer

2019 - 2020
Self-employed
  • Created and deployed deep learning classification service using PyTorch, scikit-learn, Kibana, PCA, Python, NumPy, and pandas.
  • Developed machine learning deployment, testing, and monitoring solution.
  • Developed a high performance debugging architecture for the manual rule-based model in an object-oriented manner.
Technologies: NumPy, Principal Component Analysis (PCA), MySQL, Kibana, Python, PyTorch

Software Engineer

2018 - 2019
Self-employed
  • Worked in an agile environment to design and develop robust scraping solutions to meet customers' requirements for functionality, scalability, and performance.
  • Modified existing scraping interfaces to fix bugs and upgrade interfaces.
  • Incorporated new features and improved runtime performance.
  • Implemented new front-end features and back-end processes.
Technologies: Web Scraping, Agile, Jira, Java, MongoDB, JavaScript

Smartfactory IoT

I used MQTT to collect data from various sensors and save the data in a data lake. Then, I built the Spring back end to serve the data through API and a front end in Angular to visualize the data in a customizable dashboard (everything on GitHub). In addition, I designed and implemented a large scaling web application, programming the front end and back end using modern design principles and technologies. Finally, I developed a predictive maintenance solution with an anomaly detection technique.

Safe Autonomous Driving

I won second place at the biggest IoT hackathon in Germany—Bosch Connected World 2018. I combined Keras-based implementation of reinforcement learning with a driver monitoring solution to enable safer autonomous driving. In addition, I implemented via supervised learning based on a self-collected dataset. The reinforcement learning agent was trained on the AirSim simulator from Microsoft using DQN.

Crypto Trading Bot

I implemented an algorithm to trade cryptocurrencies such as Bitcoin and automated trades using the Binance API. Further on, I utilized web scraping technologies to mine additional data from various websites for live volatility and index pricing.
2016 - 2019

Bachelor of Technology Degree in Computer Science

THM University of Applied Sciences - Germany

Languages

Python, SQL, JavaScript, Java, PHP

Libraries/APIs

Scikit-learn, PyTorch, Pandas, NumPy, XGBoost, Flask-RESTful

Tools

Git, Kibana, Jira, Apache Airflow, AWS CLI

Paradigms

Agile

Platforms

Ubuntu, Visual Studio Code (VS Code), Jupyter Notebook, Docker, Kubernetes, Google Cloud Platform (GCP)

Other

Natural Language Processing (NLP), Machine Learning, Web Scraping, Processing & Threading, Natural Language Understanding (NLU), GPT, Generative Pre-trained Transformers (GPT), Convolutional Neural Networks (CNN), Artificial Intelligence (AI), Image Recognition, Computer Vision, Principal Component Analysis (PCA), Reinforcement Learning, Vertex

Frameworks

Flask, Hadoop

Storage

MySQL, MongoDB, Elasticsearch

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