Lead Data Scientist - Credit Risk Modeling & Transformers

Klarna; Milano; In loco; EUR 65.000 - 93.000; Tempo pieno

Descrizione del lavoro

Klarna is expanding its Next Generation Modeling Techniques team in Milan. You will train transformer-based models on long sequences of transactional data, design tokenisation schemes for numerical, categorical, and temporal features, and own the model lifecycle from data prep to production.

You should understand transformer architectures, work with Python, PyTorch, SageMaker and Airflow, and be ready to own problems end to end in a fast-moving fintech environment.

Competenze

• You've designed tokenisation schemes for heterogeneous feature types, such as numerical, categorical, and temporal data, in a sequence model.
• You've taken a model through its full lifecycle before, from training through to serving it in production.
• You work with Python, PyTorch, SageMaker, and Airflow day to day.

Mansioni

• Train transformer-based models on long, real-world sequences of Klarna's transactional and behavioural events.
• Design tokenisation schemes for numerical, categorical, and temporal features, deciding on vocabulary size and sequence length.
• Own the model lifecycle end to end, from data preparation and training through to serving it in production.
• Translate research decisions into production systems that guide other Klarna ML teams.

Descrizione del lavoro

Klarna is expanding its Next Generation Modeling Techniques team in Milan. You will train transformer-based models on long sequences of transactional data, design tokenisation schemes for numerical, categorical, and temporal features, and own the model lifecycle from data prep to production.

You should understand transformer architectures, work with Python, PyTorch, SageMaker and Airflow, and be ready to own problems end to end in a fast-moving fintech environment.