About the role
Lead Data Scientist at Klarna in Milan, on the Next Generation Modeling Techniques team. The job is to train an in-house transformer on Klarna's own sequences of transactions, logins, and events, then reuse that customer representation in consumer credit underwriting. They are not fine-tuning a public LLM. The patterns they need are not in those training sets.
You work close to the architecture: how to tokenise a purchase amount, a merchant category, and a timestamp into one sequence the model can learn from, then carry that decision into a production system. Small team, high ownership, research through to something that actually scores customers.
Highlights
- Milan onsite, Klarna credit ML.
- Transformer and sequence modeling on in-house data, not a wrapper around a public LLM.
- Lead seat, research to production.
- No salary disclosed.
This recap is dataskew's editorial summary, not the company's copy.