At a Glance
- Tasks: Develop and improve credit risk models, analyse performance, and drive lending decisions.
- Company: GOCAP, a fast-growing lender focused on sustainable personal loans.
- Benefits: Hybrid work model, competitive salary, and direct impact on lending strategies.
- Other info: Collaborative environment with high visibility and ownership from day one.
- Why this job: Join a dynamic team and shape the future of data-driven lending.
- Qualifications: 5+ years in credit risk modelling, advanced Python and SQL skills required.
The predicted salary is between 70000 - 90000 £ per year.
London | Full-time | Hybrid (2 days in office)
About GOCAP
GOCAP is building a different kind of lender. We provide salary-linked personal loans designed around real affordability and repayment sustainability. We are live in market, growing quickly, and using data to improve how lending decisions are made. This is a hands-on role within a small team where your work will directly influence underwriting, pricing, portfolio performance and customer outcomes. We are looking for someone analytical and pragmatic. The role is more than just building good models. We value practical, explainable and operationally effective credit risk solutions that drive strategic value to the business. You will have key input in this process.
The role
You will work closely with the VP of Credit across credit lifecycle, helping to develop and improve the analytical approaches that drive our lending decisions. This includes building models, analysing performance, and identifying opportunities to improve how we assess and manage risk in practice.
What you’ll do
- Work within AWS-based production environments, including testing, maintaining and supporting changes across credit decisioning workflows and Lambda-driven processes
- Analyse originations, arrears, defaults, cures and portfolio trends
- Build and improve credit risk and decisioning models with bureau, open banking and internal lending data
- Analyse and maintain structured loan and portfolio data tapes
- Produce clear, decision-ready insights from imperfect or incomplete datasets
- Support implementation and refinement of underwriting strategies
- Build monitoring and reporting to track model and portfolio performance
- Work closely with risk, product and engineering to operationalise changes
- Investigate data quality, segmentation and performance issues
- Support model governance, validation and documentation
What we’re looking for
- 5+ years building, calibrating and productionising credit risk models in live decisioning environments, with demonstrated experience beyond traditional scorecard methodologies (e.g. machine learning, hybrid/ensemble or data-driven segmentation approaches)
- 3+ years’ experience working within AWS-based decisioning environments, including testing and supporting changes across production workflows and services such as Lambda.
- 2+ years’ experience working in lending or live credit decisioning environments
- Advanced Python and SQL skills are mandatory
- Experience working with real-world and imperfect datasets
- Understanding of underwriting, scorecards, portfolio analytics or risk strategy
- Strong analytical and problem-solving skills
- Ability to explain analysis clearly and commercially
- Comfortable working in a fast-moving environment with high ownership
Particularly valuable
- Experience in fintech or bureau functions
- Hands on experience in analysing bureau and transactional data (e.g. open banking)
- Experience implementing or monitoring production credit models
- Understanding of lending trade-offs beyond pure model performance metrics
- Familiarity with model monitoring, segmentation and performance stability
- Ability to challenge assumptions and defend analytical reasoning constructively
What to expect
- A small, fast-moving and highly collaborative environment
- Direct exposure to live lending decisions and portfolio performance
- High visibility and ownership from day one
- Opportunity to help shape how a growing lender uses data in decisioning
Apply
Please send your CV along with a short note outlining: the type of analytical work or models you have implemented, your experience in working within AWS-based environments, your relevant lending or credit risk experience and why the role interests you.
Please note: You must have the right to work in the UK. We are unable to provide visa sponsorship.
Senior Data Scientist | Credit Risk employer: GOCAP
At GOCAP, we pride ourselves on being an innovative lender that values data-driven decision-making and employee empowerment. Our hybrid work culture fosters collaboration while allowing for flexibility, and we offer significant opportunities for professional growth within a fast-paced environment. Join us in shaping the future of lending with your analytical expertise, where your contributions will directly impact our success and customer outcomes.
StudySmarter Expert Advice🤫
We think this is how you could land Senior Data Scientist | Credit Risk
✨Tip Number 1
Network like a pro! Reach out to people in the industry, especially those at GOCAP or similar companies. A friendly chat can open doors and give you insights that a job description just can't.
✨Tip Number 2
Prepare for interviews by brushing up on your technical skills. Be ready to discuss your experience with AWS, Python, and SQL. We want to see how you can apply your knowledge to real-world problems, so think of examples that showcase your analytical prowess.
✨Tip Number 3
Showcase your problem-solving skills! During interviews, be prepared to tackle case studies or hypothetical scenarios related to credit risk. This is your chance to demonstrate how you think critically and make data-driven decisions.
✨Tip Number 4
Don’t forget to apply through our website! It’s the best way to ensure your application gets seen. Plus, it shows you’re genuinely interested in being part of our team at GOCAP.
We think you need these skills to ace Senior Data Scientist | Credit Risk
Some tips for your application 🫡
Tailor Your CV:Make sure your CV is tailored to the role. Highlight your experience with credit risk models and AWS environments, as these are key for us. Use specific examples that showcase your analytical skills and how you've made an impact in previous roles.
Craft a Compelling Note:In your short note, be clear and concise about your relevant experience. We want to know what analytical work you've done, especially in lending or credit risk. Show us why this role excites you and how you can contribute to our mission.
Showcase Your Skills:Don’t forget to highlight your advanced Python and SQL skills! These are mandatory for us, so make sure they stand out in your application. If you have experience with real-world datasets, mention that too!
Apply Through Our Website:We encourage you to apply through our website for a smoother process. It helps us keep track of applications better and ensures you don’t miss any important updates from us. Plus, it’s super easy!
How to prepare for a job interview at GOCAP
✨Know Your Models Inside Out
Make sure you can discuss the credit risk models you've built in detail. Be ready to explain your approach, the data you used, and how you validated your results. This role values practical and operationally effective solutions, so highlight how your models have driven strategic value.
✨Familiarise Yourself with AWS
Since this position involves working within AWS-based environments, brush up on your knowledge of AWS services, especially Lambda. Be prepared to discuss any hands-on experience you have with testing and supporting changes in production workflows.
✨Prepare for Real-World Scenarios
Expect questions that challenge your analytical reasoning. Think about how you would handle imperfect datasets or real-world scenarios. Show that you can produce clear insights from incomplete information and explain your thought process clearly.
✨Show Your Collaborative Spirit
This role requires close collaboration with various teams. Be ready to share examples of how you've worked with risk, product, and engineering teams in the past. Highlight your ability to communicate complex analyses in a way that everyone can understand.
