Data Scientist

Provenir

32d•Remote

About The Position

Provenir is the unified Decision Intelligence Platform that gives enterprises full control over end- to-end customer decisioning — to manage risk, drive growth, and transform business outcomes. By consolidating data, AI models, intelligence, agents and governance into a single decisioning environment, Provenir empowers business teams to configure and evolve strategy directly, while maintaining enterprise-grade reliability and regulatory compliance. Trusted by 120+ institutions in 60+ countries, Provenir processes over 4 billion decisions annually — turning architectural coherence into sustained risk performance and measurable value. Ready to solve meaningful challenges, work with enterprise customers, and help shape the future of AI-powered decisioning? Join us. About Global Applied Intelligence Global Applied Intelligence (GAI) is the team that turns Provenir's platform capability into measurable client outcomes. We deploy data science, applied AI, and delivery expertise directly into client engagements, operating as trusted advisors and technical partners, not back-office implementers. GAI operates through regional business partnerships supported by global practices, meaning the right expertise reaches every engagement regardless of geography.

Requirements

Bachelor’s degree in a STEM field plus a minimum of 3 years of experience in data science, analytics, decision science, applied machine learning, or a related field; or a master’s degree or equivalent experience in a related STEM field.
Strong Python skills, including experience with pandas, scikit-learn, notebooks, data wrangling, and model development workflows.
Experience building, validating, or interpreting supervised machine learning models.
Strong data manipulation skills, including merging, cleansing, sampling, profiling, and preparing data for analysis.
Ability to balance model performance, explainability, complexity, and business usability.
Good understanding of common model evaluation concepts such as AUC, precision, recall, lift, stability, and model monitoring.
Ability to translate analytical outputs into clear insights and recommendations.
Strong communication skills in Portuguese and English; Spanish language skills are a plus and would help strengthen regional coverage across LATAM.
Comfortable communicating with internal stakeholders and open to working directly with clients as part of project delivery and discovery.
Curious, proactive, and willing to learn new business domains, analytical methods, and platform capabilities.
Organized and delivery-focused, with the ability to manage multiple priorities in a fast-moving environment.

Nice To Haves

Experience in financial services, fintech, banking, lending, payments, insurance, telecommunications, or another data-rich industry.
Exposure to client-facing work, workshops, product demonstrations, or cross-functional business discussions.
Experience with MLOps, model deployment, APIs, MLflow, CI/CD, or production model governance.
Familiarity with credit risk, fraud, collections, or customer management use cases.
Experience preparing presentations, technical documentation, or business summaries for data science initiatives.

Responsibilities

Support LATAM engagements across a range of data science, analytics, and decisioning use cases.
Work with internal teams and, where appropriate, clients to understand business problems, data availability, analytical requirements, and expected outcomes.
Build, evaluate, and explain analytical solutions, including predictive models, scorecards, decision rules, segmentation analysis, simulations, and business insights.
Use Python and common data science libraries to clean, explore, transform, and analyze data.
Help prepare analytical outputs, client-ready insights, model performance summaries, and business recommendations.
Contribute data science input to discovery, workshops, demonstrations, and delivery activities, with support from more experienced team members.
Help explain how machine learning, rules, explainability, monitoring, and decisioning can be applied within the Provenir platform.
Communicate technical concepts clearly to both technical and non-technical audiences.
Document analysis, assumptions, code, and recommendations in a clear and reproducible way.
Follow and contribute to team best practices for code quality, documentation, version control, testing, and reusable delivery assets.
Collaborate with global Data Science colleagues to share learnings, improve internal approaches, and support consistent delivery across regions.