Lead Credit Risk Data Scientist
Role details
Job location
Tech stack
Job description
As a Lead Data Scientist within the Credit Data Science team, you will serve as a domain expert responsible for the end-to-end design, development, and productionization of robust, scalable machine learning solutions for our credit and portfolio management domain. This role requires a deep understanding of the business and the ability to apply your expertise to the most pressing challenges, driving a direct and measurable impact on Billie's P&L. Reporting directly to the VP of Data Science and based in Berlin, this is a senior technical leadership role; you will own Billie's credit risk modeling domain end-to-end end-to-end, work in close partnership with Engineering, Product, and Data Science peers, and play a central role in shaping and executing on the roadmap for state-of-the-art ML models and applied AI that power our fast-growing business.
In more detail, you will:
- Take ownership over one of the most important KPIs leading to Billie's success, directly impacting our P&L with your expertise.
- Drive the technical solution and execution of high-quality, impactful ML solutions across multiple domains within the Data Science team, ensuring project success from conception to production.
- Identify and apply advanced AI methodologies to push Billie's credit scoring capabilities beyond conventional approaches, turning emerging techniques into production-ready solutions (e.g. LLMs, RAG, AI agents, foundation models).
- Apply exceptional hands-on expertise in quantitative analysis, data mining, data science, and advanced ML to model complex business patterns, build state-of-the-art credit risk models (PD, LGD, EAD, etc), identify risk factors, and optimize Billie's real-time decision engine logic for various use cases.
- Define and execute the analytics for complex, cross-domain problems, including developing hypotheses for experimentation, designing A/B tests, and synthesizing results into actionable insights.
- Partner closely with Engineering, Product, and Data Science teams to enhance and optimize the decision engine, improving its logic, integrating new data sources, and enhancing functionalities. You will be a key voice in technical discussions across team boundaries, ensuring credit risk thinking is embedded in how Billie builds its systems.
- Mentor and grow junior Data Scientists within the team, and bring a technical perspective to system design discussions across backend and ML, ensuring credit risk solutions are built for scale from the ground up.
Requirements
- 6+ years of Data Science experience, with significant exposure to the credit domain and deep expertise in PD modeling: from scorecard development and model validation through to production monitoring. Broader experience with LGD, EAD, limit policies, and portfolio management is strongly preferred.
- Hands-on proficiency in Python (pandas, scikit-learn, XGBoost, PyTorch/TensorFlow) and SQL (Snowflake, BigQuery, etc.), and experience with data visualization tools like Tableau.
- Hands-on experience working with LLMs and generative AI, with the ability to evaluate, integrate, and fine-tune models in a production environment.
- Proven experience leading the deployment and productionization of ML services, demonstrating a deep understanding of modern MLOps concepts like containerization (e.g., Docker, Kubernetes), event-driven architectures, and model monitoring.
- Hands-on experience with graph databases (e.g., Neo4j) to model, analyze, and extract features from highly interconnected data is also highly desired.
- Strong business acumen and the ability to translate complex business problems into clear analytical and technical requirements that deliver maximum value.
- Excellent communication and data storytelling skills, with a track record of maximizing the impact of technical findings on organizational decision-making.
- A strong product mindset: you're comfortable owning a roadmap, making trade-offs under uncertainty, and driving initiatives forward with minimal direction, translating business ambition into a clear technical plan.