Nubank is the leading fintech in Latin America. Using bleeding-edge technology, design and data, the company aims to fight complexity and empower people to take control of their finances. We are disrupting an outdated and bureaucratic system by building a simple, safe and 100% digital environment that addresses Brazilian customers’ needs with no paperwork, bank branches or inefficient call centers.
Our headquarter is located in São Paulo, Brazil, and we are also present in Berlin, Germany with an engineering office. With a team of over 1,200 of the most innovative professionals in technology, Nubank is dedicated to create an inclusive, international and challenging work environment.
Model Review Chapter
Nubank is a fintech that is rethinking financial services in Brazil. We have several proprietary algorithms that predict responsiveness to a vary of customer behaviors, therefore solving major company challenges and continuously improving customer experience. These models need to be monitored and interpreted in order to ensure the best results are delivered while maintaining appropriate risk levels.
What are the challenges Model Reviewers face at Nubank?
- Address the most important issues and risks considering their relevance
- Develop model intuition and interpretation
- Model and feature monitoring to detect anomalies and deviations
- Facilitate interactions and communication among stakeholders
- Identify out-of-the-box or non-trivial risks. What could happen out of normal conditions or extreme cases? Which risks could be caused by unanticipated interactions between models?
- Evaluate model consistency or its capacity to deliver stable results
- Understand the trade-off between simplicity and performance
- Review and assess risks associated with development, testing, use and implementation of models
- Follow up with model owners to monitor and resolve findings
- Leverage your coding skills to automate risk evaluation
- Perform reviews to monitor and evaluate changes to models and present recommended actions
- Seek and engage state-of-the-art standards throughout the modeling process
- Coordinate with team members and management on risk program activities and status
- Execute multiple risk program activities simultaneously against established timeframes
- Engage in interaction with model owners, model developers and regulatory personnel
- Assist with education and training on risk program and requirements
We believe in:
- Good team chemistry;
- Enthusiasm for finding opportunities to improve models;
- Capacity to keep learning new things while constantly improving what we are already good at;
- Collaborating efficiently to ship a great product experience to our customers.
You will fit well if:
- You want to be an owner
- You are hungry and enjoy being constantly challenged to learn and do more
- You embrace conflict of ideas and like to question the status quo
- You learn quickly and easily adapt to changing situations and priorities
- You believe in building phenomenal products and doing great work by international standards
- You want to understand the big picture, to be held accountable and make a meaningful contribution with your work
Examples of relevant skills we value:
- Solid statistical and math skills.
- Ability to develop intuition on models and understand business purpose and context
- Work experience and solid understanding of Data Science and Machine Learning models, including common families of models, feature engineering, feature selection and other practical machine learning issues, such as overfitting
- Ability to understand and evaluate risks;
- Good coding skills. Experience in Scala, Python, Clojure and other similar languages is a plus
- Working knowledge of SQL, Hive, Pig, or other query languages
- Business skill to understand how each model fits in a bigger context
- Ability to understand trade-offs and prioritize
- Strong analytical and problem-solving skills
- Excellent interpersonal skills and a team player
- Work independently and coordinate with the work of others
- Well organized and detail oriented to handle diverse and concurrent assignments