Senior Data Scientist - Credit Risk Modeler - #4
Summary
Muttdata, a remote-first data/ML services startup, seeks a Senior Data Scientist to own and evolve a live credit-score (Hit/No Hit) model for a beverage-industry client — retraining gradient-boosting models, evaluating AUC-ROC/F1/calibration, segmenting risk, and productionizing the model with Python, XGBoost, MLflow, and Databricks.
🚀 Join Our Remote Data Products & Machine Learning Startup! 🚀
At Muttdata, we build innovative Data Products and Machine Learning solutions that help companies solve complex business challenges. As a fast-growing, remote-first startup, we're passionate about technology, collaboration, and continuous learning.
This opportunity is with a leading multinational beverage company based in Mexico City.
We are looking for a Senior Data Scientist - Credit Risk Modeler to join our team 🐶🚀. You'll inherit, maintain, and evolve our Credit Score model (Hit / No Hit), applying credit-risk modeling expertise to segment the portfolio by probability of default and enable dynamic credit lines.
This role works closely with data and platform teams, taking ownership of a live financial model and evolving it responsibly. Strong statistical rigor, business understanding of credit risk, and ownership are essential to succeed in this fast-paced, collaborative environment.
🚀 What We Do
- Leveraging our expertise, we build modern Machine Learning systems for demand planning and budget forecasting.
- Developing scalable data infrastructures, we enhance high-level decision-making, tailored to each client.
- Offering comprehensive Data Engineering and custom AI solutions, we optimize cloud-based systems.
- Using Generative AI, we help e-commerce platforms and retailers create higher-quality ads, faster.
- Building deep learning models, we enhance visual recognition and automation for various industries, improving product categorization, quality control, and information retrieval.
- Developing recommendation models, we personalize user experiences in e-commerce, streaming, and digital platforms, driving engagement and conversions.
🌟 Our Partnerships
- Amazon Web Services
- Astronomer
- Databricks
🌟 Our Values
- 📊 We are Data Nerds
- 🤗 We are Open Team Players
- 🚀 We Take Ownership
- 🌟 We Have a Positive Mindset
Responsibilities 🤓
- Take ownership of the existing model (tree ensembles / gradient boosting), retrain it, and incorporate new features (e.g., digital payments, CISP).
- Evaluate performance (AUC-ROC, F1, probability calibration) and segment risk levels A–F aligned with credit standards.
- Calculate dynamic credit lines and expected loss (risk exposure), integrating score, potential, and sales history.
- Package the model under the MFL framework (PyFunc, model_card, tests) for productionization.
Required Skills 🚀
- Proven experience in credit risk / scoring models and supervised machine learning.
- Python (scikit-learn, XGBoost), statistics, model validation, and MLflow.
- Understanding of risk metrics (PD, expected loss, exposure).
Nice to Have Skills 😉
- Experience in financial services, credit bureaus, or commercial credit portfolios.
- Experience developing AI agents / agentic infrastructure (e.g. Mosaic AI Agent Framework, agent orchestration, MCP).
Skills
As published by lever · 12 questions · 9 written answers
Basics
Resume/CV, Full name, Email, Phone, Current location, Current company, LinkedIn URL, GitHub URL, Other URL
Pick from a list (3)
- Do you currently reside in Mexico or Latin America? (This is a mandatory requirement for this role. If you do not currently reside in Latin America or Mexico, your application will not be considered.)
- English Level optional
- Working mode optional
Written answers (9)
- Describe about your relevant experience in the role optional
- Have you worked with credit-risk or scoring models? Could you briefly describe an approach you used to build and validate one? optional
- Do you have experience evaluating ML models in a risk environment? Could you briefly share how you handle metrics like AUC-ROC or probability calibration? optional
- Do you have experience with risk segmentation or expected-loss concepts (PD, LGD, EAD)? Could you briefly walk us through a practical example? optional
- Do you have experience using Python (scikit-learn, XGBoost) and MLflow for model tracking? Could you briefly summarize your background with these tools? optional
- Have you ever taken ownership of an existing production model? Could you briefly outline your process for updating, retraining, or redeploying it? optional
- Do you have experience using Databricks (or Databricks Feature Store) for feature engineering and governance? Could you briefly share how you used it?
- Study/Degree optional
- Gross net salary expectations (USD) optional