Quantitative Engineer - Credit Modelling

Bislab is a rapidly scaling AI-native innovator in credit assessment and intelligent algorithm solutions, focused on creating sophisticated, API-first products for organizations with complex needs. We have big ambitions for the future and are looking for more exceptional talent to join us on our journey.

Type
Full-time
Location
Oslo, Norway

About Bislab

Bislab is building Norway's most advanced credit intelligence platform. We hold the country's richest dataset on individuals and companies and use it to help companies make better credit decisions, fight fraud and automate risk management. We're AI-native, product-obsessed, and growing fast.

The team is small, senior, and technically exceptional. We have large ambitions for the future and are looking for more exceptional talent to join us on our journey.

The Role

You'll join our Quant team, owning credit modelling and other risk models at Bislab. That means building and maintaining the quantitative models at the heart of our products.

This is a hands-on, high-ownership role. You'll work with real data at scale - a performance-focused python library, and a dataset that covers the financial behaviour of virtually every entity in the Nordics.

What You'll Do

  • Design, build, and maintain credit scoring and risk models of both companies and persons.
  • Work hands-on in a modern Python stack, using tooling and packages like `uv`, `ty` and `polars` on Norway's richest person and company dataset on advanced ML applications 
  • Own the full modelling lifecycle: ideation, feature engineering, training, validation, monitoring, and iteration
  • Develop backtesting frameworks and champion/challenger setups to validate model performance
  • Contribute to how we think about data, model risk, and analytical infrastructure as we scale
  • Translate complex model outputs into clear insights for product and commercial stakeholders

What We're Looking For

  • Strong foundation in quantitative methods, statistics, probability, and machine learning
  • Proficiency in Python; experience with dataframe libraries like Polars or Pandas
  • Experience building predictive models in a production setting and maintaining across the MLOps lifecycle
  • Comfort working with messy, high-dimensional real-world data
  • The instinct to own a problem end-to-end, not just hand off deliverables
  • Curiosity about the intersection of classical credit risk and modern ML/AI techniques
  • Ability to communicate technical work clearly to non-technical audiences
  • Eager adopter and experience with using modern AI tools to automate boilerplate, so you can focus on the important decisions

Why Join Bislab?

  • Richest dataset in the Nordics: full-population coverage of all entities, updated continuously
  • Real ownership: you set the direction on credit modelling, not just execute on someone else's spec
  • AI products and internal tools: work alongside an AI product team that is serious about pushing the frontier, and a tech team building and adopting AI tools to accelerate development
  • Early-stage upside: equity stake in a fast-scaling company with strong commercial traction
  • Small, high-trust team: no bureaucracy, no slowdowns, no meaningless meetings

Interested? Apply or reach out informally. Not ready to apply but want to talk through the role? Drop us a line at careers@bislab.no.

Careers

Build with us

Immerse yourself, innovate and build a global leader in intelligent risk solutions alongside Scandinavia’s most committed and gifted technologists.

Quantitative Engineer - Credit Modelling

Full-time
 -
Oslo, Norway
Learn more

Senior Sales Manager

Full-time
 -
Oslo, Norway
Learn more

Senior/Principal Software Engineer, AI

Full-time
 -
Oslo, Norway
Learn more

Senior/Principal Software Engineer

Full-time
 -
Oslo, Norway
Learn more

Get in touch

Intelligent Risk Solutions

Learn how Bislab can help you improve your credit risk processes and increase efficiency. We will be in touch shortly.

Thank you! We'll get back to you shortly.
Oops! Something went wrong.