Senior Data Scientist

Description

Leega is a company focused on delivering efficient and innovative customer service. This could not be any different with our primary fuel: people! Our culture is inspiring, and our values are present in everyday life: ethics and transparency, quality excellence, teamwork, economic, social and environmental responsibility, human relationships, and credibility. We seek innovative professionals who are driven by challenges and focused on results. If you are looking for a dynamic and collaborative company that invests in its employees through continuous training, Leega is the place for you! **>> LEEGA IS FOR EVERYONE — we would be thrilled to welcome you to our team. Join us in writing our story and building our future.** Apply now to our open positions! **Responsibilities and duties** **About the opportunity** You will transform demand, occupancy, and purchasing behavior data into models that price a network comprising thousands of origin-destination pairs and multi-leg routes — a scientifically rich revenue management problem involving perishable seat inventory, strong seasonality, no-shows, and regulatory caps. This role centers on discovery: formulating hypotheses, rigorously validating them statistically, and driving revenue and margin at the scale of millions of trips per year. **Your challenges** * **Exploratory analysis and EDA —** conduct exploratory and statistical analysis to uncover patterns, formulate hypotheses, and guide modeling. * **Demand forecasting —** model demand and no-show rates per origin-destination pair using gradient boosting and time series methods, correcting for censored demand bias (unconstrained demand). * **Elasticity and willingness-to-pay —** estimate price elasticity and willingness-to-pay by segment and route, forming the foundation for price optimization. * **Network-level revenue management —** model seat protection and capacity allocation (fare buckets) across multi-leg routes, balancing occupancy and revenue. * **Causal experimentation —** design A/B tests and causal inference frameworks that validate pricing changes and measure true uplift, with clear statistical promotion criteria. * **Explainability and trust —** ensure model interpretability (e.g., SHAP) to justify each price decision to business stakeholders and regulators. * **Cold start and calibration —** design strategies for routes with limited historical data, starting from literature-based priors and evolving toward ML solutions, per tenant. *You are the bridge between science and product: collaborating with ML engineers on productionization, with data engineers on data availability, and with commercial and operations teams on goal definition.* **Requirements and qualifications** **Stack & Tools** * **Languages & libraries:** Python (pandas, NumPy, scikit-learn, statsmodels), XGBoost, LightGBM * **Statistics & classical ML:** EDA, statistical modeling, regression, classification, clustering * **Deep learning:** PyTorch, TensorFlow * **Causal & temporal modeling:** time series/forecasting, causal inference (e.g., EconML, DoWhy), Bayesian/hierarchical modeling * **Revenue management & optimization:** elasticity, fare buckets / seat protection, linear programming * **Experimentation, MLOps & data:** A/B testing, JupyterHub, MLflow, Ray Tune; SHAP, SQL, Cube.js on Athena **What we’re looking for** **Essential** • Strong quantitative background (Statistics, Economics, Mathematics, Engineering, Computer Science or related) and solid foundation in probability, statistical inference, and experimental design. • Exploratory data analysis (EDA) and strong storytelling and visualization skills. * Classical ML (regression, classification, clustering) and time series; familiarity with deep learning (PyTorch or TensorFlow). * Python and the Data Science ecosystem (pandas, scikit-learn, statsmodels); SQL for large-scale data. * Causal inference and/or A/B testing and impact measurement. * Clear scientific communication and comfort with AI-assisted development (Claude Code). **Nice-to-have** * Revenue management or pricing experience in transportation, aviation, or hospitality (canonical RM domains). • Operations research and optimization (linear programming; Gurobi, HiGHS or OR-Tools). • Applied deep learning (PyTorch, TensorFlow) — e.g., demand modeling with embeddings or sequential models. • Causal ML (EconML, DoWhy) and Bayesian/hierarchical modeling (PyMC, Stan). • Reinforcement Learning (especially offline RL) and the Ray ecosystem. • Graduate degree (Master’s/PhD) and experience with LLMs/RAG. **Additional information** **Remote work** **Project duration:** 6 months, with possibility of extension/internalization. At Leega, we don’t just deliver lines of code or dashboards. We transform complex technological challenges into real-world impact. With over 15 years of experience, we combine the depth of human expertise with the speed of Artificial Intelligence to build solutions that transform businesses — and, above all, improve people’s lives. We are a technology consulting firm — agnostic and strategic. With offices in Brazil and Europe, our team of over 580 multidisciplinary talents lives and breathes the Data Analytics, Cloud, and AI ecosystem. We master the full stack — from Governance to Engineering — ensuring technology is not merely a tool, but a sustainable competitive advantage for the market’s top players.