How our customers benefit

We combine academic know how with industrial implementation.

Innovative, pragmatic, and experienced
We have multiple years of experience in AI research and the ability to implement it in production. We have already designed and implemented solutions reaching over 100 million users a day.
Measurable Results
It is important to us that incorporating AI in products adds a measurable value. Proper metrics and KPIs help us deliver a better product.
Newest findings from AI research
Our machine learning experts make use of the latest results from AI research.
Technology Independent
We have experience with a wide variety of technology stacks and cloud solutions. Together we will choose technologies which are best suited for your company and the particular project.
A One Stop Shop
We cover the entire AI topic: from consulting to final implementation.
Security and Compliance
Our solutions conform to the highest security standards and apply to the EU-GDPR regulations. We will support you to become cloud ready with anonymized user data.
Custom Solutions
We believe that custom solutions should deliver the best possible results. Our holistic and iterative approach allows us to develop the best possible services and products.
Small Teams
Our multidisciplinary teams cover all aspects of the product development cycle. We have experienced product managers, software developers and data scientists.
Working Culture
We are a decentralized, remote-first company. This allows us to work with the best experts worldwide. Our main location is in Berlin, Germany. We believe in flat hierarchies, high responsibility and participation, constant education, diversity, fair compensation and flexible working hours.
Start-Up Culture
We have supported various startups from their very beginning. We know the strategic and economic risks of digital transformation from our own experience. Both the customer as well as market focus are very important to us.


Some of the technologies we use on a daily basis

Use Cases

Some of our previous projects.


For SoundCloud we developed recommender systems, spam detection systems and optimized their search ranking. We designed the systems from scratch, implemented and maintained them.

From big data processing to model training to prototyping and online A/B testing. The solutions had to scale up to hundreds of millions of users. The models were trained on billions of data points.

We were involved in building up SoundCloud’s data organisation and had an essential influence on SoundCloud’s success.



For Idagio we designed and implemented a music recommender system from scratch. The final model is a deep neural network and was based on YouTube’s production recommender system.

The model is using various input signals such as metadata information, collaborative filtering signals as well as the raw audio data itself.

The system had to scale up to millions of audio tracks.


Muru Music

For Muru Music we built a system to classify audio tracks into their main and sub genres. The system was trained on multiple large scale production catalogues from BMG, Sony and Warner. A total of 2 million tracks were used to train the model.

In order to deal with these data set sizes we built a data platform on top of Google Cloud Services. All pipeline steps were fully automates: preprocessing of the audio, model training, model prediction and rich evaluation. This data platform enabled us to quickly run experiments and iterate on the model.

We used a deep convolutional neural network which operated directly on the raw audio features. No high level features were used.



BSDEX is a crypto exchange platform and a daughter company of the stock exchange Stuttgart. BSDEX wanted to become a data driven organization and asked us to assist them.

In order to do that we introduced new technologies and moved parts of the old infrastructure into the AWS cloud.

Technology is just one part in order to become a data driven organization. More importantly is to enable the people. For that sound processes and an appropiate organizational structure needs to be in place. We decided to organize the company around a data mesh and defined neccessary data processes.

Technology and enabled People helped BSDEX to get the most value out of their data.