Senior Data Scientist

This is a fully remote position, open to applicants in Brazil.

📋 Description

• Transform data related to demand, occupancy, and purchasing behavior into pricing models for numerous origin-destination pairs and multi-leg routes.

• Conduct exploratory and statistical analyses to identify patterns, formulate hypotheses, and inform modeling initiatives.

• Model demand and no-shows utilizing gradient boosting and time-series techniques, while adjusting for censored-demand bias.

• Estimate price elasticity and willingness to pay based on segment and route.

• Model seat protection and capacity allocation for multi-leg routes, optimizing both occupancy and revenue.

• Design A/B tests and apply causal inference methodologies to validate pricing adjustments and assess uplift.

• Ensure model interpretability, employing SHAP, to substantiate pricing decisions to both the business and regulatory bodies.

• Develop strategies for cold-start and calibration for routes with limited historical data.

• Collaborate with machine learning engineers, data engineers, as well as commercial and operations teams.

• Formulate and validate hypotheses with statistical rigor, influencing revenue and margins across millions of trips annually.

⛳️ Requirements

• Strong quantitative background in Statistics, Economics, Mathematics, Engineering, Computer Science, or a related discipline.

• Solid understanding of probability, inference, and experimental design.

• Experience in exploratory data analysis (EDA), storytelling, and data visualization.

• Knowledge of classical machine learning techniques, including regression, classification, and clustering.

• Familiarity with time-series analysis.

• Experience in deep learning using frameworks like PyTorch or TensorFlow.

• Proficiency in Python and the Data Science ecosystem, including libraries such as pandas, scikit-learn, and statsmodels.

• SQL expertise for handling large-scale datasets.

• Knowledge of causal inference and/or A/B testing along with impact measurement.

• Strong scientific communication skills.

• Comfortable using AI-assisted development tools like Claude Code.

• Familiarity with XGBoost, LightGBM, EconML, DoWhy, MLflow, Ray Tune, SHAP, Cube.js, and Athena.

• Experience or knowledge in elasticity, fare buckets/seat protection, linear programming, and revenue management is advantageous.

• A graduate degree (Master’s or PhD) and experience with LLMs/RAG are beneficial.

🏝️ Benefits

• Ongoing professional development opportunities.

• Potential for project extension or permanent employment following the six-month project period.

• Remote work flexibility.