Senior Data Scientist Reinforcement Learning - Offer Intelligence (m/f/d)

You'll build and bring into production state-of-the-art probabilistic models that power millions of pricing and offer decisions at SIXT every day. You'll own the full lifecycle, from shaping the analytical question to deploying live models, supported by an innovation-friendly culture.

• You architect and prototype advanced regression models (linear, GLM, mixed-effects, Gaussian Process) with a principled Bayesian approach, guiding pricing strategy at scale
• You design and productionise personalisation and recommendation systems - two-tower retrieval, embedding-based candidate generation, learning-to-rank, sequential/transformer models - with contextual bandits and off-policy evaluation to keep them learning from real interactions
• You apply techniques like SVI, MCMC, and importance sampling to enable robust decision-making under uncertainty, even with sparse, high-volume, or streaming data
• You build and maintain reproducible pipelines for feature engineering, label generation, and automated data validation using tools like Airflow or Dagster, ensuring high code quality and reliability
• You deploy models via FastAPI, Docker, or Kubeflow, and establish real-time monitoring with Bayesian control charts and performance dashboards to catch drift and anomalies early
• You design sophisticated A/B and multivariate tests, apply quasi-experimental and causal impact methods, and quantify the value of information to balance exploration and exploitation
• You collaborate with product, revenue, and customer experience leaders to translate ambiguous ideas into testable hypotheses, while mentoring peers and elevating Bayesian practice through internal publications and workshops

• Expertise You bring deep statistical chops, with 5+ years of applying regression, hierarchical models, or state-space methods in production
• Computing proficiency You have a well-stocked Bayesian toolbelt - fluent in PyMC, Stan, NumPyro, TFP, or similar - and are comfortable writing custom likelihoods and priors
• Modeling You have proven experience scaling inference using SVI, black-box VI, or advanced MCMC techniques on large datasets
• Engineering practices You write solid, production-grade Python code and are familiar with type hints, testing frameworks, and CI/CD workflows
• Infrastructure You are hands-on with cloud platforms like AWS, GCP, or Azure, and have experience with containerization (Docker/K8s) and workflow orchestration
• Stakeholder management You communicate uncertainty, lift, and risk in plain English for executives, while engaging deeply with scientists and engineers

• Personalisation (nice to have) You have experience with recommender and personalisation stacks - two-tower / embedding retrieval, learning-to-rank, sequential models, contextual bandits - plus counterfactual or off-policy evaluation to prove incremental value rather than optimise click-through

• A Global Tech Hub in Lisbon
• Learning & Knowledge Exchange
• Flexible Work Setup
• Two office days a week, flexible hours, and modern spaces built for both deep focus and team collaboration
• Time Off & Wellbeing
• Enjoy 28 vacation days per year, an additional day off on your birthday, one volunteer day annually, and private health insurance that also covers your spouse and children free of charge
• Practical Everyday Benefits
• Get a yearly Coverflex allowance and a daily meal allowance to make everyday life a little easier
• SIXT Perks
• Get exclusive rates on all SIXT services, with special discounts extended to your family and friends

Resumo organizado por IA a partir do anúncio original. Confirma os detalhes no site da empresa.