Senior Data Scientist II - Personalization

Careem is building the Everything App for the greater Middle East — making it easy to move around, order food and groceries, manage payments, and more. Our purpose is simple: to simplify and improve people’s lives and build an awesome organisation that inspires. Since 2012, Careem has enabled earnings for over 2.5 million Captains, simplified the lives of more than 70 million customers, and built a platform where the region’s best talent and entrepreneurs thrive. We operate in 70+ cities across 10 countries, from Morocco to Pakistan. We’re now entering our next chapter — one powered by AI. We’re looking for AI talent: curious problem-solvers who know how to apply AI to build tools, automate workflows, and create real impact. Whether it’s streamlining operations, enhancing customer experience, or reimagining internal systems — we want people who can make Careem work smarter and move faster. About The Team: The Personalization team sits within Careem's Data Science organization and owns the AI systems that decide what every user sees, in what order, and why across Food, Quik, and Shops. Our mission is to build the hyper-personalization layer for the Careem app: real-time, cross-vertical recommendation and ranking systems that learn from a user's behavior in one vertical and apply that understanding everywhere else they engage with Careem. As one of the senior technical leads on this team, you'll help define how Careem thinks about personalization at a regional scale working alongside the region's top data science talent, and pushing the state of the art using graph-based retrieval, transformer architectures, and real-time learning. What You'll Do: - Own hyper-personalization use cases across Food, Quik, and Shops designing systems that learn a user's intent and preferences in real time and transfer that signal across verticals, so a user's behavior on one product makes every other product smarter. - Be a technical lead on Careem's exploration of graph-based retrieval methods for recommendations including evaluating and building knowledge graph pipelines that power candidate generation and ranking at scale. - Design and evaluate transformer-based architectures (XFY) for sequential and contextual recommendation moving Careem's ranking and retrieval stack beyond classical ML toward deep, attention-based models. - Push toward online/streaming learning systems that adapt to user behavior within a session, not just from batch-trained models refreshed on a daily cadence. - Identify where personalization signals, models, or infrastructure can be shared across Food, Quik, and Shops rather than rebuilt per vertical reducing duplicate work and compounding the value of every experiment. - Be part of a 0-to-1 AI transformation for the Careem app from a personalization standpoint shaping how generative AI and LLM-based systems augment retrieval and ranking. - Build a long-term vision for how Careem rethinks customer acquisition and engagement strategies, grounded in data-driven decision-making. - Drive exploratory analysis to understand user behavior across verticals, identifying new levers to move metrics and building behavioral models that inform product enhancements. - Shape and influence the ML models and instrumentation that optimize the product experience, surfacing new areas of opportunity and new product directions. - Provide product leadership through data-driven recommendations communicating the state of the business, root-causing metric movements, and using experimentation results to influence product and business decisions. - Implement scalable machine learning algorithms that run in production on large-scale data. - Run exploratory data analysis to better understand user and business phenomena, and to discover untapped areas of growth and optimization. - Answer complex analytical questions from large datasets to help shape Careem's products and services. - Define and track key metrics for specific personalization initiatives. - Design and run randomized controlled experiments (A/B tests), analyze results, and communicate findings to cross-functional teams. - Continually challenge the status quo investigating new data processing technologies, retrieval architectures, and learning paradigms, and ensuring the team operates at industry-leading standards. - Build and deploy retrieval-augmented generation (RAG) systems and other applications of large language models within the personalization stack. What You'll Need: - 7-10 years of experience in data mining, predictive modeling, time series analysis, machine learning, and Big Data methodologies, including transformation and cleaning of structured and unstructured data. - Advanced degree in a quantitative discipline such as Physics, Statistics, Mathematics, Engineering, or Computer Science. - Solid experience with deep learning techniques including attention mechanisms, retrieval models, and transformer-based architec

6-8 years of experience in data mining, predictive modeling, time series analysis, machine learning, and Big Data methodologies, including transformation and cleaning of structured and unstructured data. Advanced degree in a quantitative discipline such as Physics, Statistics, or Mathematics.

Drive real-time, cross-vertical personalization: Own hyper-personalization use cases across Food, Quik, and Shops designing systems that learn a user's intent and preferences in real time and transfer that signal across verticals. Advance graph-based retrieval: Be a technical lead on exploration of graph-based retrieval methods for recommendations including evaluating and building knowledge graph pipelines that power candidate generation and ranking at scale. Build next-generation ranking models: Design and evaluate transformer-based architectures (XFY) for sequential and contextual recommendation moving ranking and retrieval stack beyond classical ML toward deep, attention-based models. Pioneer real-time learning: Push toward online/streaming learning systems that adapt to user behavior within a session. Build for cross-learning: Identify where personalization signals, models, or infrastructure can be shared across Food, Quik, and Shops. Be part of a 0-to-1 AI transformation for the Careem app from a personalization standpoint shaping how generative AI and LLM-based systems augment retrieval and ranking. Build a long-term vision for how Careem rethinks customer acquisition and engagement strategies, grounded in data-driven decision-making. Drive exploratory analysis to understand user behavior across verticals, identifying new levers to move metrics and building behavioral models that inform product enhancements. Shape and influence the ML models and instrumentation that optimize the product experience. Provide product leadership through data-driven recommendations communicating the state of the business. Implement scalable machine learning algorithms that run in production on large-scale data. Run exploratory data analysis to better understand user and business phenomena, and to discover untapped areas of growth and optimization. Answer complex analytical questions from large datasets to help shape Careem's products and services. Define and track key metrics for specific personalization initiatives. Design and run randomized controlled experiments (A/B tests), analyze results, and communicate findings to cross-functional teams. Continually challenge the status quo investigating new data processing technologies, retrieval architectures, and learning paradigms, and ensuring the team operates at industry-leading standards. Build and deploy retrieval-augmented generation (RAG) systems and other applications of large language models within the personalization stack.