Data Scientist (Machine Learning)

About the role

Nelo is reimagining credit to expand consumer buying power in Mexico, and this role sits at the intersection of rigorous statistics and high-impact product decisions. As the Data Scientist (Machine Learning) you will own the design and deployment of causal inference models that directly drive underwriting and portfolio management strategies. You will build the core engine for credit pricing, personalization, and ranking, ensuring your algorithms balance risk and opportunity with mathematical precision. You will lead ML infrastructure projects to ensure production-grade observability and operational excellence for every model you ship. You will translate complex theoretical concepts into production-ready code that influences who gets access to credit in an emerging market. This position demands comfort with high-stakes constrained optimization where "good enough" solutions are not acceptable. If you want to apply academic-level rigor to a rapidly scaling P&L, this seat is for you.

Key facts

What you'll do

• Design and deploy causal inference models to drive underwriting and portfolio management strategies, moving beyond correlation to actionable, risk-aware insights.
• Build and refine the core algorithms for credit pricing, personalization, and ranking that directly impact consumer wallet and company margin.
• Lead ML infrastructure projects to ensure observability, reliability, and operational excellence for the models you own from experimentation to production.
• Write production-grade Python and SQL that scales, ensuring your code meets strict standards for performance, security, and maintainability.
• Partner closely with product and engineering to translate ambiguous business problems into well-defined data science experiments with measurable outcomes.
• Run rigorous experiments at scale, analyzing results to guide product decisions and optimize key risk and revenue metrics for the business.
• Translate complex statistical theory into clear narratives and actionable recommendations for both technical and non-technical stakeholders.
• Own the end-to-end lifecycle of models, from hypothesis formulation and feature engineering through validation, monitoring, and iterative improvement.
• Champion best practices in model documentation, versioning, and testing to support long-term maintainability and auditability.
• Act as a technical leader within a small, high-performing engineering team, mentoring peers and elevating the overall standard of analytical rigor.

Requirements

You must hold a strong academic background with a deep theoretical understanding of classification, forecasting, and optimization, with a PhD strongly preferred. You need at least 5 years of hands-on experience applying statistical learning and machine learning methods in production environments. You must be fluent in writing production-grade Python and SQL, with a proven track record of shipping models that impact real business outcomes. You should understand the first principles of classification, forecasting, and optimization, and be able to explain their assumptions and limitations. You must value velocity, recognizing that a great model deployed quickly often outperforms a perfect model delivered too late. You need to be comfortable working in an in-office setting in New York City, collaborating closely with cross-functional teams on whiteboards and in real time. You should be comfortable making decisions under uncertainty and communicating tradeoffs clearly to both technical and executive audiences. You must be based in or willing to relocate to New York City to fulfill the in-office requirement.

Nice to have

Experience with constrained optimization techniques applied to credit risk or financial decisioning.

Background in fintech, credit, or payments domains.

Familiarity with modern ML infrastructure tools and MLOps best practices.

Contributions to open source or technical publications that demonstrate thought leadership.

Practical notes

This is an in-office role based in New York City.

The engagement is full-time.

The application process includes a quick chat with the hiring manager, a business case or technical assessment relevant to the role, an onsite interview in NYC to meet the team, and an offer stage.