Applied machine learning
I develop and evaluate machine-learning models, with experience in computer vision, recommendation systems, and medical image analysis.
Johannes Roth
I'm a machine learning engineer and PhD researcher in Leipzig. I build computer-vision systems, data pipelines, and software for research.
My research at the Max Planck Institute and University of Giessen studies how vision models relate to human brain activity. Before that, I worked on computer vision at CHECK24, medical machine learning, and product matching for e-commerce.
Available from January 2027 · View CV
Hello from the other side! If you're here, it means you want to learn more about me personally - so I'll keep things more casual!
Here you'll find some info about me and my hobbies, my taste in music, movies and books, and some notes on things I'm thinking about.
Expertise
Data engineering
I build pipelines for collecting, processing, and organizing large datasets for machine learning and research.
Software engineering
I design and build web applications, APIs, and research software, including their deployment and maintenance.
Research
I study how vision models relate to human brain activity, combining computational modelling, statistical analysis, and fMRI experiments.
Experience
PhD Researcher
Machine learning and computational neuroscience
Hebart Lab · MPI for Human Cognitive and Brain Sciences & University of Giessen
Independent research on vision models and their relationship to human brain activity, combining computational analyses with fMRI experiments. Developed methods for model evaluation and experimental design, GPU-based data pipelines, and public research software. Supervised working students and interns.
Python · PyTorch · CLIP · scikit-learn · SLURM · Docker
Research Assistant - ML in Medicine
Medical imaging models, segmentation, and uncertainty estimation
ScaDS.AI Dresden/Leipzig
Developed and evaluated deep-learning models for brain-tumor segmentation, including a multi-plane UNet++ ensemble. Also built mortality-prediction models for clinical data, with uncertainty estimation.
PyTorch · FT-Transformer · SAINT · UNet++
Data Scientist / ML Engineer
Production ML service for hotel images and travel product data
CHECK24 (Travel Vertical)
Independently designed and deployed a computer-vision service processing 20 million hotel images, including seasonal image classification. Prototyped image retrieval, duplicate detection, and image-quality assessment. Reduced recommendation-data update time by over 95% through incremental processing.
Python · PyTorch · Flask · Redis · PHP · BigQuery · Grafana
Full-stack Developer
Django sites, Linux hosting, and deployment automation
Kimetric UG
Designed and delivered the Hebart Lab and THINGS Initiative websites. Gathered client requirements and handled implementation, deployment, Linux hosting, and maintenance.
Django · Nginx · Gunicorn · Linux · CI/CD
Data Scientist
Product matching, scraping, and model evaluation workflows
Webdata Solutions GmbH (now Vistex)
Developed machine-learning models for product matching and image classification in e-commerce. Improved image-based matching accuracy from 12% to 83% against a classification baseline in an internal cross-retailer evaluation.
Python · TensorFlow · PostgreSQL · AWS
Data Analyst
Cloud data warehouse, ETL testing, and reporting workflows
Mercateo Services GmbH & Co. KG
Developed data-integration, reporting, and testing workflows for an AWS-based data warehouse, using Apache NiFi and Pentaho.
AWS · Apache NiFi · Python · Pentaho · Java · R
Education
M.Sc. Computer Science
Machine learning, data analysis, and medical image processing
Leipzig University
Focus on machine learning, data analysis, and medical image processing; grade 1.2. Master's thesis applied generative deep learning to study visual processing in the human brain (grade 1.1).
B.Sc. Business Information Systems
Software engineering, data systems, and business
Leipzig University
Studied distributed systems, data management, e-commerce, and economics; grade 1.5.
Selected Projects
I developed pipelines to identify naturalistic photographs in large web-image datasets, including classification, quality checks, and GPU-based feature extraction. The public release includes image embeddings for visual similarity search.
thingsvision provides a common interface for extracting features from different vision models, making it easier to compare their representations. My contributions include software architecture, model integration, and memory efficiency.
LAION-fMRI supports research on how the brain represents natural images. I developed and maintained the public website and data-download services, using AWS S3, access controls, and short-lived download links.
I developed the public website and cloud-based data services, and built annotation tools for working students and interns. I also contributed to data preprocessing, organization, and labeling.
Publications
- 2026 Characterizing Universal Object Representations Across Vision Models
We analyzed the object similarity structure of 162 diverse vision models to ask what, if anything, converges across architectures, objectives, and datasets. The paper separates universal from model-specific dimensions and links the more universal structure to interpretability, semantic image properties, macaque IT activity, and human similarity judgments.
- 2025 How to sample the world for understanding the visual system
How does the choice of images affect what we can learn about the visual brain? We developed a large reference set of naturalistic photographs and compared image-sampling strategies, using simulations and fMRI data to study dataset coverage and model generalization.
- 2025 Ten principles for reliable, efficient, and adaptable coding in psychology and cognitive neuroscience
A practical guide to research software, covering project organization, testing, documentation, version control, and collaboration. The principles distinguish exploratory prototyping from the work needed to make code reliable and reusable.
- 2025 Fine-grained image and category information in ventral visual pathway
Show older publications Hide older publications fMRI methods, GAN-based neuroscience, brain tumor segmentation
- 2023 High stimulus presentation rates for fMRI
- 2021 Preferred stimuli for individual voxels in the human visual system
For my master's thesis, I used generative deep learning to synthesize images predicted to activate particular regions of the human visual system. The work combined a model of brain activity with a generative image model to investigate visual selectivity.
- 2022 Multi-plane UNet++ Ensemble for Glioblastoma Segmentation
Recognition / service
2025 CMBB Replication Award for reliable coding practices in neuroscience
2023–2024 PhD student representative elected to represent 180+ doctoral researchers at MPI CBS
2024/25 CNNvis interactive CNN visualization used for public ML outreach at Gießen Science Days About Me
Movement
My love for moving my body started with joining a breakdance crew at the age of 17. Since then I've dabbled in all kinds of movement disciplines. Today, I really enjoy bouldering, but I also do resistance training, yoga and more recently Qi Gong (good way to wake up the body in the morning!). I also love hiking in nature (and combining it with climbing is the best way to spend a day, see above).
Music
A couple of years ago, I asked a bunch of friends, "Hey, want to start a band?" To my surprise, everyone said yes! We had to drag our front singer into it, but now he regularly screams his heart out. We mostly play pop punk covers for friends' birthday parties, but the dream of writing our own songs is still alive and kicking.
Food
As a kid, one of my teachers would say "Johannes lives off plain air", because I refused to eat food from the school kitchen. Either I was very picky, or the food was just plain bad. Today I eat almost anything - but I love throwing together a plate of whole food ingredients into something delicious. Lately, I enjoyed hosting friends for dinner nights, which have been a blast (but surprisingly stressful!).
Meditation
I've been meditating for over a decade now - although it's an on-off relationship. I even attended a 10-day silent meditation retreat in 2024, which has been pretty life changing for me! This is an image from the forest near the meditation hall - I walked that path probably 100 times and discovered something new every time.
Shelves
Currently reading
Art & Fear
The Mind Illuminated
Music
I listen to lots of stuff - but Spotify knows me best, so here is my weekly discovery playlist for your perusal.
Movies
Once a month, my wife and I do a horror movie night with friends - here are the last three movies we watched (pulled from my Letterboxd account). Also, check out the recommender I built for us.
Loved
Silence 
Old Path White Clouds 
You Are Here 
No Mud, No Lotus 
Peace Is Every Step 
When Things Fall Apart 
Full Catastrophe Living 
Wherever You Go... 
Why We Meditate 
The Art of Living 
Be Here Now 
After the Ecstasy, the Laundry 
The Attention Revolution 
The Book: On the Taboo 
The Wisdom of Insecurity 
Autobiography of a Yogi 
Doors of Perception 
The Psychedelic Explorer's Guide 
Food of the Gods 
Red Rising series 
The Kingkiller Chronicle 
A Song of Ice and Fire series 
The Expanse series 
The Belgariad series 
Mistborn series 
The 13th Paladin series 
The Three-Body Problem 
Dune 
It 
Island 
Malice 
Of Blood and Fire 
Gods of the Wyrdwood 
Magician 
The Dwarves 
Uldart: Die dunkle Zeit 
A Wizard of Earthsea 
Ender's Game 
Braiding Sweetgrass 
Wild 
Into the Wild 
Into Thin Air 
Seven Years in Tibet 
Born to Run 
A Search in Secret India 
Adult Children of Emotionally Immature Parents 
How to Do the Work 
Why Has Nobody Told Me This Before? 
Why Zebras Don't Get Ulcers 
Maybe You Should Talk to Someone 
In the Realm of Hungry Ghosts 
How to Change Your Mind 
DARE 
Feeling Good 
A Liberated Mind 
Four Thousand Weeks 
Deep Work 
The Myth of Normal 
How Not to Die 
How Not to Age 
Food Rules 
Omnivore's Dilemma 
Deep Medicine 
Total Immersion 
24/6 
Smartphone Nation 
It Doesn't Have to Be Crazy at Work 
The Age of Surveillance Capitalism 
How to Break Up with Your Phone 
Make Time 
We Should All Be Feminists 
Men Explain Things to Me 
The Road to Reality 
Surely You're Joking, Mr. Feynman! 
Tools of Titans 
How to Win Friends and Influence People 
The Life-Changing Magic of Tidying Up 
When Breath Becomes Air 
Man's Search for Meaning 
That Good Night Found Okay
The Obstacle Is the Way 
Stolen Focus 
The Wim Hof Method 
Atomic Habits 
Indistractable 
Waking Up 
Built to Move 
Kitchen Confidential 
The Comfort Crisis 
The Shallows Notes
See all postsIt's always clear from the outside
A passage from Art and Fear and what it says about how we see other people's work versus our own.
$200 for a glimpse into the future (existential crisis included)
A month with Claude Max taught me how work, science, and life will change radically in the very near future.
Say Hi
Happy to hear from friends, collaborators, future coworkers, or people who want to talk about brains, tools, climbing, books, or dinner. Email is best.
Get in Touch
Happy to chat about research, potential collaborations, or opportunities. Email is best. Also on LinkedIn, GitHub, Hugging Face, and Google Scholar.