SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Fetcherr builds responsible AI that transforms market complexity into measurable profit growth through its proprietary Market Model—an AI-powered system delivering 96% forecast accuracy and real-time decision intelligence. The company's glass-box architecture uses market data with full transparency, deployed first in global aviation with corporate partners including Delta, Virgin Atlantic, WestJet, Viva, and Azul, delivering consistent average profit uplift of 7%.
The Price Optimization (PO) team translates insights into decisions by working with large-scale customer data and market predictions to drive revenue management decisions. The team builds and maintains the decision-making engine: designing data pipelines that ingest customer data and running it through an optimization engine that simulates the market—weighing competition, pricing constraints, inventory availability, predictive models, and each client's unique business policies—to generate optimal price recommendations.
As a Data Scientist Engineer, you will design and implement the decision-making logic of the Price Optimizer, focusing on translating complex business rules into mathematical models and production-ready Python code. Your primary mission is building the "brain" of the system, working at the intersection of Data Science and Product to ensure simulation and optimization engines accurately reflect real-world pricing strategies and market dynamics.
Key responsibilities include: implementing business logic by translating intricate pricing rules and commercial strategies into robust Python code and mathematical constraints; refining optimization models by developing and tuning simulation and revenue management algorithms that drive pricing recommendations; writing clean, tested, and maintainable code to core logic repositories; analyzing and improving by using data to validate model behavior and identify edge cases where business rules clash with algorithmic outputs; and collaborating with Solution Architects to define logic requirements and with Data Engineers to integrate models into Dagster pipelines.
While you will write production code, you will rely on Data Engineers for ETL pipeline orchestration and distributed compute scaling. Quality, reliability, and attention to detail are essential—recommendations must be accurate before reaching clients.
