Senior Data Scientist (Search)

Emerging Travel Group is a pioneering travel-tech company known globally for its brands — RateHawk, ZenHotels, and RoundTrip. It offers customers more than 2.7 million accommodation options in 220 countries. Founded in 2010, the company employs over 3,500 people across Europe, the Americas, the Middle East, the CIS, and South Africa, focusing on product development and multilingual customer support to innovate travel products.

• Experience managing end-to-end ML projects in production.
• Strong knowledge of classical ML including feature engineering, boosting algorithms, classification/regression, cross-validation, threshold tuning, and calibration.
• Experience with search or recommendation systems.
• Experience with deep learning frameworks such as PyTorch and TensorFlow, including fine-tuning and inference.
• Proficient in writing production-grade Python code with testing and understanding of model packaging and service integration.
• Understanding of ML monitoring including metrics, drift, alerts, diagnostics, and support.
• Proficient in SQL for dataset building (joins, window functions).
• Experience with model interpretability and error analysis.
• Familiarity with experiment tracking tools such as MLflow, Weights & Biases, or DVC.
• Experience with orchestration/pipelines such as Airflow, Prefect, or Dagster and advanced data processing.
• Conversational English.

Nice to have:

• Experience with neural networks applied to vector search, ranking, NLP, or computer vision.
• Experience with Big Data technologies like Hadoop and Spark.

• Manage end-to-end ML projects: problem definition, solution design, testing, production deployment, and support.
• Collaborate with data engineers to build datasets, define data requirements, and assess feasibility and risks.
• Work with data analysts to design and analyze A/B tests, including metrics, splits, result interpretation, and rollout recommendations.
• Develop and train classical ML and deep learning models.
• Deploy models and code to production as Python services and support integration and releases.
• Monitor post-launch model quality, including tracking metrics, drift/degradation, and implementing improvement and support processes.