Hybrid Senior Data Scientist – Dynamic Pricing, Revenue Optimization

at Accelya Group

• Job title: Senior Data Scientist – Dynamic Pricing, Revenue Optimization
• Job type: Full Time
• Experience level: Senior
• Salary: Not specified
• Degree requirement: Bachelor's Degree
• Tech skills: Airflow, AWS, Cloud, EC2, Python, Spark
• Location requirements: Hybrid, Colombia

About the role

• Senior Data Scientist at Accelya optimizing pricing models for airlines. Involving demand forecasting, model deployment, and cross-functional collaboration.

Responsibilities

• Build and maintain demand-forecasting and marginal-revenue models used to produce opportunity costs (bid prices) at route/flight/segment granularity.
• Derive customer segments with clustering, embeddings, and rule-based approaches that are predictive of purchase behavior.
• Develop conditional choice / purchase-probability models that control for endogeneity. Design and interpret natural or randomized experiments where applicable, using IVs, control-function approaches, double ML, or structural methods as needed.
• Integrate forecasted demand, choice probabilities and bid price constraints into an optimization layer (deterministic optimization, dynamic programming, or gradient-based methods).
• A/B/Experimentation & measurement: design online/offline evaluation frameworks and randomized experiments to validate price strategies, measure revenue impact, and control risk.
• Production & MLOps: deploy models and optimizers into low-latency production pipelines (APIs/real-time scoring), implement monitoring for model performance, price sensitivity drift and KPI alerts.
• Cross-functional delivery: communicate results and trade-offs to RM/product/stakeholders and translate business requirements into model constraints and instrumentation.

Requirements

• 4+ years industry experience building demand forecasting, pricing, or choice models for e-commerce, travel, retail, or similar.
• Strong applied econometrics / causal inference skills (experience with IVs, double ML, or structural estimation).
• Experience with discrete choice / purchase probability models (MNL, nested logit, or neural networks) or demonstrably equivalent approaches.
• Hands-on experience building forecasting pipelines (classical and ML approaches) and producing demand or marginal revenue estimates.
• Experience exposing ML models and optimization as production services (low-latency inference) and implementing monitoring/alerts.
• Strong coding skills in Python.
• Familiarity with cloud platforms and tools: AWS (S3, EC2, SageMaker), Databricks/Spark, Airflow, and MLflow or similar.
• Experience designing and analyzing A/B tests and uplift experiments; strong statistical hypothesis testing skills.
• Excellent communication: can explain causal assumptions, model limitations, and pricing trade-offs to RM and product stakeholders. Fluent English: Interviews will be held in this language.

Benefits

• Health insurance
• Paid time off
• Flexible working arrangements
• Professional development