Benjamin Meyer, Developer in Binningen, Switzerland
Benjamin is available for hire
Hire Benjamin

Benjamin Meyer

Verified Expert  in Engineering

Data Scientist and Developer

Binningen, Switzerland

Toptal member since October 17, 2022

Expertise
Machine LearningData AnalysisPythonJavaDeep LearningNumPyScalaTensorFlowPlay FrameworkMicroservices DevelopmentAlgorithmsGit
Bio

Benjamin is a part-time guest lecturer at the University of Applied Sciences and Arts Northwestern Switzerland, teaching machine learning. He is a skilled and passionate programmer focusing on machine learning and data science. Having good communication skills with the ability to adapt to various audiences, Benjamin can break down complex topics and explain them in simple terms.

Portfolio

University of Applied Sciences Northwestern Switzerland
University Teaching, Python 3, Scikit-learn, TensorFlow, Machine Learning...
KeeValue AG
Java, Python 3, Scikit-learn, Gradient Boosting, Machine Learning...
ADVANCIENCE AG
Scala, Play Framework, Akka, Akka Persistence, Event Sourcing, CQRS...

Experience

  • Python 3 - 6 years
  • Machine Learning - 6 years
  • Data Science - 5 years
  • Scikit-learn - 5 years
  • Deep Learning - 3 years
  • Scala - 3 years
  • TensorFlow - 2 years
  • Keras - 2 years

Availability

Part-time

Preferred Environment

MacOS, PyCharm, Scrum, Jupyter Notebook

The most amazing...

...thing I've developed is a house pricing model based on image data and crawled web data as a driving force in all aspects of development.

Work Experience

Guest Lecturer

2020 - PRESENT
University of Applied Sciences Northwestern Switzerland
  • Taught machine learning concepts, algorithms, and interrelationships for three whole days each semester as part of the advanced studies program in data science.
  • Evaluated and graded a bachelor thesis as an external machine learning expert.
  • Created slides with many visualizations hosted on GitHub, github.com/benikm91/cas_machine-learning-slides.
  • Prepared and supervised the machine learning labs—programming exercises on real datasets.
Technologies: University Teaching, Python 3, Scikit-learn, TensorFlow, Machine Learning, Deep Learning, Reveal, Python

Data Scientist | Full-stack Developer

2020 - 2022
KeeValue AG
  • Developed a lifecycle cost module that used and combined other modules to predict the total lifecycle costs of a building with only a little information about it.
  • Created a model to predict the distribution of the necessary intervention level on building elements based on age and condition and planned modifications on a building.
  • Developed a model with little data about the dismantling costs of a building. Used constraints motivated by domain knowledge to improve model performance.
Technologies: Java, Python 3, Scikit-learn, Gradient Boosting, Machine Learning, Data Analysis, Data Management, Data Engineering, Data Science, Python

Full-stack Developer

2019 - 2020
ADVANCIENCE AG
  • Designed a microservice architecture and data management system for logging events, which was later used for analytical tasks.
  • Developed a full back-end infrastructure with CI for logging events with Scala and Akka. Used event sourcing services to develop it fast and flexibly for future analysis.
  • Created a platform's website with OAuth 2.0 login mechanism with an external service.
  • Reviewed analytics service developed by a colleague and found a bug. The average was calculated before the non-linear transformation and transformed afterward, which was not the same as calculating the average of the non-linearly transformed values.
Technologies: Scala, Play Framework, Akka, Akka Persistence, Event Sourcing, CQRS, TypeScript 3, Angular, HTML5, CSS, Unity3D, PostgreSQL, Cassandra, ScalaTest, Software Architecture, Microservices, Docker, Continuous Integration (CI), OAuth 2

Scientific Assistant at the Institute for Data Science

2018 - 2019
University of Applied Sciences Northwestern Switzerland
  • Joined an ongoing project about predicting house prices based on images. As the test set performance was surprisingly good, I checked and found duplicates.
  • Created a deep learning proof of concept for a possible project about predicting customs numbers based on item descriptions. Thanks to my proof of concept, the client later submitted this project.
  • Corrected exercises and held exercise classes on bachelor's subjects such as efficient algorithms and machine learning.
Technologies: Deep Learning, Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Transformer Models, Machine Learning, Gradient Boosting, Random Forests, Graph Algorithms, Python 3, Jupyter Notebook, Scikit-learn, Python

Experience

AlexNet Implementation

AlexNet was implemented in TensorFlow based on the original paper and trained on the CIFAR-100 dataset. It was a side project where I analyzed different activation functions and later discovered additions to sharpen my understanding. I also visualized the learned filters of trained CNN.

Restricted Boltzmann Machine in Scala

https://github.com/benikm91/RestrictedBoltzmannMaschine
A side project while completing the Neural Networks for Machine Learning course on Coursera. I implemented the restricted Boltzmann machine with the CD1 learning algorithm. The restricted Boltzmann machine was trained on MNIST to generate images from numbers from zero to nine.

Slides for Machine Learning Class

https://github.com/benikm91/cas_machine-learning-slides
As a part-time lecturer at FHNW, I created a set of slides with visualizations to explain better some algorithms, concepts, and interconnections between algorithms. The slides are created with reveal.js, Angular, TypeScript, HTML, and CSS and are hosted on my GitHub.

Education

2020 - 2022

Master's Degree in Computer Science

University of Basel - Basel, Switzerland

2014 - 2017

Bachelor's Degree in Computer Science

University of Applied Sciences and Arts Northwestern Switzerland (FHNW) - Brugg, Switzerland

Certifications

APRIL 2020 - PRESENT

Reactive Architecture (1)-(6)

Lightbend

MAY 2018 - PRESENT

Neural Networks for Machine Learning

Coursera

MAY 2016 - PRESENT

Machine Learning

Coursera

Skills

Libraries/APIs

Scikit-learn, Matplotlib, Pandas, TensorFlow, NumPy, Keras, OpenMP, MPI, SciPy, PyTorch

Tools

Seaborn, PyCharm, Git, ScalaTest, TensorBoard

Languages

Python 3, Java, Python, Scala, Haskell, TypeScript 3, HTML5, CSS

Platforms

Jupyter Notebook, MacOS, Docker

Frameworks

Play Framework, Akka, Angular, Unity3D, OAuth 2, Spark

Paradigms

Event Sourcing, CQRS, Microservices, Scrum, Compiler Design, REST, Continuous Integration (CI)

Storage

PostgreSQL, Cassandra

Other

Machine Learning, Data Science, Convolutional Neural Networks (CNNs), Data Analysis, Deep Learning, Recurrent Neural Networks (RNNs), Akka Persistence, Software Architecture, GitFlow, Bayesian Inference & Modeling, Algorithms, Scientific Data Analysis, SOAP, Transformer Models, Gradient Boosting, Random Forests, Graph Algorithms, Data Management, Data Engineering, University Teaching, Reveal, Restricted Boltzmann Machine (RBM)

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