Senior Data Scientist II - Personalization

About Careem

Team and role

Personalization and machine learning

• Own cross-vertical personalization use cases and build real-time systems that learn and transfer user intent across products.
• Evaluate and build graph-based retrieval and knowledge graph pipelines for recommendation candidate generation and ranking.
• Design and evaluate transformer-based architectures for sequential and contextual recommendations.
• Advance online and streaming learning that adapts to user behaviour within a session.
• Find reusable personalization signals, models, and infrastructure across Food, Quik, and Shops.
• Shape generative AI and LLM applications in retrieval and ranking, including RAG systems.
• Build production machine learning algorithms for large-scale data and explore new processing technologies and learning approaches.

Analytics and product leadership

• Build a long-term vision for data-driven customer acquisition and engagement.
• Analyse user behaviour across verticals, build behavioural models, and identify opportunities for growth and product improvements.
• Shape ML models and instrumentation to optimize product experience and identify product opportunities.
• Communicate data-driven recommendations, explain business performance, investigate metric movements, and influence product and business decisions.
• Answer complex analytical questions, define and track initiative metrics, and design, analyse, and communicate randomized controlled experiments and A/B tests.

Experience and education

• 7–10 years in data mining, predictive modelling, time-series analysis, machine learning, and Big Data methods, including structured and unstructured data transformation and cleaning.
• Advanced degree in a quantitative discipline such as Physics, Statistics, Mathematics, Engineering, or Computer Science.
• 2–4 years of industry experience in personalization, recommendation, or search is required; product-driven, scaled-company experience is preferred.
• Strong problem-solving and coding skills; knowledge of A/B testing, classical ML, deep learning, and end-to-end recommendation, ranking, and retrieval systems.

Technical skills

• Deep learning experience including attention, retrieval models, and transformer architectures applied to ranking or recommendation.
• Proficiency in Python, SQL, Spark, and Hive.
• Database experience with technologies such as Hadoop, BigQuery, Amazon EMR, Hive, Oracle, SAP, DB2, Teradata, MS SQL Server, or MySQL.
• BI and visualization experience with tools such as Tableau, MicroStrategy, ChartIO, or Qlik.
• Knowledge graphs, graph neural networks, and graph-based retrieval are a strong plus; online or streaming learning familiarity or interest is also a strong plus.
• Geospatial data processing skills are a plus.

Work arrangement

• The role works four days a week in the office and one day from home.
• The posting also states colleagues can work remotely from any country for 30 days a year.

Benefits

• Benefits include healthcare, fitness reimbursements, learning opportunities, and unlimited vacation days per year.