Simon is currently unavailable
Simon Tietze
Verified Expert in Engineering
Data Scientist and Developer
Berlin, Germany
Toptal member since November 17, 2022
Bio
Simon is a data scientist with experience in deep learning, machine learning, statistics, big data, and method development. Over his career, he has worked in various fields, including adtech, molecular biology, telecommunication networks, and hardware reliability. Simon has built predictive machine learning systems, reporting dashboards, and in-depth analytical reports, ranging from small datasets to systems operating in real time with thousands of requests per second.
Portfolio
iMouse GmbH / Fraunhofer HHI
PyTorch, Hugging Face Transformers, Video Transformers, Raspberry Pi...
Unnamed Global Orthodontics Company
PyTorch, Healthcare
Agado Live
PyTorch, Video Transformers, Docker, Amazon Web Services (AWS), Healthcare
Experience
- Artificial Intelligence (AI) - 20 years
- Neural Networks - 20 years
- Machine Learning - 20 years
- Data Science - 20 years
- Deep Learning - 15 years
- Python 3 - 10 years
- Deep Neural Networks (DNNs) - 10 years
- PyTorch - 10 years
Work Experience
CTO
2025 - 2026
iMouse GmbH / Fraunhofer HHI
- Designed and built an end-to-end system for automated home cage observation of lab mice, incorporating 48 cameras across 12 cages.
- Implemented a Raspberry Pi edge compute solution with a diskless fleet and full remote observability.
- Developed a fully custom multi-camera, multi-frame Deformable DETR for mouse tracking and action segmentation.
Technologies: PyTorch, Hugging Face Transformers, Video Transformers, Raspberry Pi, Deep Learning, Artificial Intelligence (AI), Ansible, Docker, Python, Statistics
Senior Machine Learning Engineer
2025 - 2025
Unnamed Global Orthodontics Company
- Developed a NeRF/Transformer hybrid model that produces high-fidelity 3D jaw models from six images for real-time dental treatment support.
- Created a working prototype in one month, from concept to validation.
- Fixed the broken codebase of the research paper on which this project was based.
Technologies: PyTorch, Healthcare
Senior Machine Learning Engineer
2024 - 2025
Agado Live
- Built an action segmentation system using fine-tuned video foundation models that automatically annotates physical therapy sessions: counting steps, analyzing posture, and providing early warnings for fall risk from uploaded patient videos.
- Deployed to production on Amazon SageMaker using a custom Docker container for MMAction.
- Optimized inference to make use of multi-core systems and stream videos without length restriction.
Technologies: PyTorch, Video Transformers, Docker, Amazon Web Services (AWS), Healthcare
Senior Data Scientist
2016 - 2018
BEN Energy
- Created customer churn models based on custom neural networks trained on censored time-to-event data. These models predicted the time until customer churn and could use partial information provided by active customers.
- Developed a SaaS predictive dashboard that provided customers with churn alerts and cross-selling recommendations.
- Presented complex modeling results to over 20 energy utility companies in interactive workshops.
Technologies: R, Python 3, Ansible, SQL, Data Science, Machine Learning, Algorithms, MySQL, PostgreSQL, Python, Neural Networks, Ggplot2, Deep Neural Networks (DNNs), Data Manipulation, Data Extraction, Large Data Sets, Data Engineering, Data Reporting, Data Analytics, Data Visualization, Bash, Generative Pre-trained Transformers (GPT), Natural Language Processing (NLP), Pandas, SQL-99, ETL, Docker, Amazon Web Services (AWS), Artificial Intelligence (AI), Statistical Analysis, Statistical Modeling, Predictive Modeling, Models, Version Control Systems, Communication, Modeling, A/B Testing, Data Analysis, Product Analytics, Data Pipelines, Product Development, Geospatial Data, REST APIs, Convolutional Neural Networks (CNNs), Statistics
Senior Data Scientist
2010 - 2015
Motorola Mobility
- Built a complex survival model integrating hardware properties with usage logs to investigate a newly released phone's high-return rates, which were due to the high-end model's target audience, not the hardware.
- Implemented an R library that assembled a concise device history from manufacturing, QA, sales, and the data used to inform multiple reporting and modeling tasks, including connecting sources in Oracle, Apache Hadoop, and BigQuery.
- Supported product launches with data on early product returns by building R Markdown templates that provided reports within days of a product coming to market.
Technologies: RStudio, R, RStudio Shiny, Python 3, Hadoop, Google BigQuery, Data Science, Machine Learning, Algorithms, Recommendation Systems, MySQL, PostgreSQL, Ggplot2, Data Manipulation, Data Extraction, Large Data Sets, Data Engineering, Google Cloud Platform (GCP), BigQuery, Data Reporting, Data Analytics, Data Visualization, Bash, SQL-99, ETL, Amazon Web Services (AWS), Artificial Intelligence (AI), Statistical Analysis, Statistical Modeling, Predictive Modeling, Models, Version Control Systems, Communication, Modeling, A/B Testing, Data Analysis, Product Analytics, Data Pipelines, Geospatial Data, REST APIs, Convolutional Neural Networks (CNNs), Statistics
Head of Analytics
2009 - 2010
Aloqa (acquired by Motorola Mobility)
- Developed an end-to-end big data analytics solution from the mobile client through Hadoop to the web reporting front end.
- Created a randomized keep-alive algorithm to deliver instant push messages to mobile clients before Google and Apple created APIs that enable this.
- Developed an early microservice architecture to scale from thousands to millions of users within weeks.
Technologies: R, Ruby, Java, SQL, Hadoop, Amazon Web Services (AWS), Statistical Analysis, Statistical Modeling, Predictive Modeling, Models, Version Control Systems, Communication, Modeling, A/B Testing, Data Analysis, Product Analytics, Data Pipelines, Product Development, Geospatial Data, REST APIs, Convolutional Neural Networks (CNNs), Statistics
Lead Developer
2007 - 2008
MoDeST
- Coordinated the development of a full-stack cheminformatics framework, including fingerprint, graph-based, ligand-ligand superpositioning, and protein/ligand docking methods.
- Implemented novel 3D visualizations for proteins based on OpenGL shaders, such as real-time ambient occlusion.
- Co-invented several novel techniques based on protein-ligand docking, e.g., inverting the normal process to look for molecular targets of known drugs.
Technologies: Java, Ruby, OpenGL, R, Statistical Analysis, Statistical Modeling, Predictive Modeling, Models, Version Control Systems, Communication, Modeling, Data Analysis, Product Development, Convolutional Neural Networks (CNNs), Statistics
Research Assistant
1999 - 2007
Ludwig Maximilians University of Munich
- Developed machine learning-based methods for automated diagnosis of vertigo-related diseases based on accelerometer recordings of upright stance.
- Worked on text mining, NLP, protein alignment extensions to profile the profile, and statistical approaches to validating lattice-based inference of text topics.
- Contributed to novel methods and applications in protein-ligand docking.
Technologies: MATLAB, R, Ruby, Java, Artificial Intelligence (AI), Statistical Analysis, Predictive Modeling, Models, Version Control Systems, Communication, Modeling, Data Analysis, Computer Vision, Convolutional Neural Networks (CNNs), Statistics, Healthcare
Project History
Population Mobility and Its Effect on the COVID-19 Pandemic in the US
Collaborated with Imperial College London on a mobility trend analysis of data grouped by user age for the entire US. We developed a pipeline combining mobile carrier and adtech location data to verify user locations. The carrier data is reliable but only precise to the cell tower level, while adtech data contains precise locations but is often fraudulent.
We used a deep learning model to augment the mobility data with user age information. The model was built and previously measured to be accurate to around 80% with five age group bins. This data was then used in a Bayesian hierarchical model analysis to attribute infection spread to different age groups in each US state.
We used a deep learning model to augment the mobility data with user age information. The model was built and previously measured to be accurate to around 80% with five age group bins. This data was then used in a Bayesian hierarchical model analysis to attribute infection spread to different age groups in each US state.
Education
2000 - 2006
Master's Degree in Computational Biology
Ludwig Maximilian University of Munich - Munich, Germany
Certifications
DECEMBER 2022 - PRESENT
Certified SAFe 5 Agile Software Engineer
Scaled Agile, Inc.
Skills
Libraries/APIs
TensorFlow, Ggplot2, PyTorch, REST APIs, Keras, Pandas, OpenGL, Hugging Face Transformers
Tools
sparklyr, Ansible, BigQuery, MATLAB
Languages
R, Python, SQL, SQL-99, Bash, Python 3, C, Ruby, Java
Platforms
RStudio, Linux, Amazon Web Services (AWS), Databricks, Google Cloud Platform (GCP), Docker, Raspberry Pi
Industry Expertise
Bioinformatics, Healthcare
Storage
Data Pipelines, Google Cloud, PostgreSQL, MySQL
Paradigms
ETL, Agile, Scrum, XP
Frameworks
Spark, RStudio Shiny, Hadoop
Other
Deep Learning, Data Science, Neural Networks, Machine Learning, Large Data Sets, Data Analytics, Data Visualization, Artificial Intelligence (AI), Predictive Modeling, Models, Communication, Modeling, Data Analysis, Product Analytics, Geospatial Data, Convolutional Neural Networks (CNNs), Statistics, Deep Neural Networks (DNNs), Algorithms, Computational Biology, Data Manipulation, Data Extraction, Data Engineering, Data Reporting, Statistical Analysis, Statistical Modeling, Version Control Systems, A/B Testing, Product Development, Computer Vision, Bayesian Inference & Modeling, Google BigQuery, Recommendation Systems, Biology, Molecular Biology, Natural Language Processing (NLP), Signal Processing, Generative Pre-trained Transformers (GPT), Video Transformers
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