Solutions / Startups
We build the machine learning in your product so your team can keep shipping everything else.
These scenarios are illustrations. None of them describes a client.
Retail and e-commerce
What we would build
A hybrid search that combines keyword matching with multilingual semantic search over the catalogue, so a query finds the right products whatever the language or wording. It runs next to the current engine and is tuned on real search logs.
OpenSearch, BGE-M3, Python
Retail and e-commerce
What we would build
A service agent that reads each ticket, looks up the order and the return policy, and drafts the reply in the customer's language. Routine answers go out after a quick check; refunds and exceptions wait for a person, with the case already summarised.
LangGraph, Zendesk API, FAISS
Retail and e-commerce
What we would build
A content pipeline that turns supplier data into product pages in German, French, Italian and English, following your tone guide and glossary. Editors review each batch side by side with the source data before publishing.
Mistral, Akeneo API, Python
Banking and finance
What we would build
A scoring model trained on past investigator decisions that ranks open alerts by risk and shows the transactions behind each score. The existing rules stay in place, the model sets the order in which people look, and its drift is checked every month.
XGBoost, SHAP, MLflow, Airflow
Pharma and life sciences
What we would build
A literature agent that queries PubMed every week for each team's topics, screens abstracts against their criteria and sends a short digest with links and the reason each paper was kept. Scientists rate the picks, which tunes the next week's screening.
PubMed API, BGE-M3, LangGraph, Microsoft Teams
A typical starting point is a notebook or a prototype that works on a laptop, and a roadmap that needs it in production. We turn it into a service with tests, evaluation and monitoring, or build it from scratch, and hand it to your engineers in a state they can extend.
One senior ML engineer from our side, working with your founders or lead developer, in your repository and your tools.
A fixed price per milestone, or a set number of days per month when you need ongoing ML capacity rather than a project.
A founder usually decides, so the first milestone can start soon after the scope is agreed.
A prototype running on your own data within a few weeks, with the numbers that show whether it is good enough to ship.
Yes. We work in your repository, follow your conventions and review process, and leave tests and documentation your team can maintain.
Usually start with an API model and measure. Fine-tuning or self-hosting is worth it when cost, latency or data rules call for it, and we show you the numbers before that decision.
Yes. Some startups need a few days of ML work a month rather than a project. We take the machine learning on your roadmap, and your team keeps ownership of the product.
You do, once the work is paid for. Tools we bring from earlier work stay ours, and you get a licence to use them inside what we built for you.
Sometimes, for the research side. Innosuisse can fund the work of a Swiss research institution, with the startup as implementation partner; our own work is billed separately. We can tell you whether your project fits.
We start with a feasibility study on your own data, so you see results before anything is promised.