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 orga…
careem · На сервисе с: 07.08.26 11:38
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:
- 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, Mathematics, Engineering, or Computer Science.
- Solid experience with deep learning techniques including attention mechanisms, retrieval models, and transformer-based architectures (XFY or similar) applied to ranking or recommendation problems.
- Working with or evaluating knowledge graphs, graph neural networks, or graph-based retrieval systems is a strong plus. Careem is actively building toward graph-based retrieval for recommendations.
- 2-4 years of industry experience in personalization, recommendation, or search is a MUST. Preferably gained in a product-driven company operating at scale.
- Strong problem-solving and coding skills.
- Solid knowledge of A/B testing methodology, classical ML, and deep learning.
- Solid understanding of recommendations, ranking, and retrieval systems end-to-end.
- Familiarity with or interest in online/streaming learning systems models that adapt within a session rather than relying solely on batch retraining, is a strong plus.
- Proficiency and demonstrated experience in Python, SQL, Spark, and Hive.
- Demonstrated experience with database technologies (e.g. Hadoop, BigQuery, Amazon EMR, Hive, Oracle, SAP, DB2, Teradata, MS SQL Server, MySQL).
- Demonstrated experience with business intelligence and visualization tools (Tableau, MicroStrategy, ChartIO, Qlik); geospatial data processing skills are a plus.
What We'll Provide You:
We offer colleagues the opportunity to drive impact in the region while they learn and grow. As a full time Careem colleague, you will be able to:
- Work and learn from great minds by joining a community of inspiring colleagues.
- Put your passion to work in a purposeful organization dedicated to creating impact in a region with a lot of untapped potential.
- Explore new opportunities to learn and grow every day.
- Work remotely from any country in the world for 30 days a year with unlimited vacation days per year.
- Access to healthcare benefits and fitness reimbursements for health activities including gym, health club, and training classes.
Похожие вакансии Data Science & ML
Управление Модельных Рисков - «by-design» уникальное подразделение, которое «видит» все AI/ML модели Банка, понимает процессы/точки принятия решений моделями, кривая обучения у наших сотрудников «круче», чем в подразделениях, разрабатывающих модели.
Наша цель – помочь Банку зарабатывать больше и улучшать клиентский опыт за счет повышения эффективности моделей и их использования в Бизнес процессах.
Мы ищем DS/Quant с экспертизой на стыке финансовой математики, торговых алгоритмов и ML для работы в напралении Модельного Риска Торговой Книги. Вы будете выступать ключевым звеном контроля качества моделей и агентов, используемых в оценке рисков и ценообразовании финансовых инструментов.
Обязанности
- оценка качества моделей ClassicML, работающих на финансовых рынках, в том числе: торговые алгоритмы, оценка эластичности по цене, кластеризация клиентов и т.д.
- проведение независимой оценки качества моделей прайсинга финансовых инструментов, а также риск-моделей (включая VaR, CVA, PFE)
- анализ корректности математических предпосылок, устойчивости моделей и их соответствия бизнес-требованиям и рыночным условиям
- оценка и контроль рисков агентов, работающих в торговых алгоритмах, процессах прайсинга финансовых инструментов и оценки рыночных рисков
- создание инструментов для автоматизации процессов мониторинга моделей и агентов с использованием Python
- подготовка аналитических заключений по результатам валидации, формирование рекомендаций по доработке моделей
- презентация результатов работы, аргументация выводов и защита предложенных решений перед разработчиками моделей, риск-менеджментом и бизнес-заказчиками.
Будет плюсом:
- навыки работы с генеративными AI-моделями; опыт создания AI-агентов и использования их в работе будет преимуществом.
Требования
- знание теории вероятностей, математической статистики и случайных процессов
- опыт работы на стороне разработки или валидации ClassicML моделей
- уверенные навыки программирования на Python, опыт разработки структурированного и поддерживаемого кода
- знание базовых принципов построения моделей прайсинга производных финансовых инструментов
- опыт работы с количественными моделями в финансах или смежных областях будет преимуществом
- участие в летних школах или курсах: Vega, ЦМФ – также является преимуществом.
Условия
- работа в удобном и современном офисе недалеко от станции метро Кутузовская
- ежегодный пересмотр зарплаты, годовая премия
- корпоративный спортзал и зоны отдыха
- более 400 образовательных программ СберУниверситета для профессионального и карьерного развития
- расширенный ДМС, льготное страхование для семьи и корпоративная пенсионная программа
- гибкий дисконт по ипотечному кредиту, равный 1/3 ключевой ставки ЦБ
- подписка Прайм с возможностью совместного использования на трёх близких
- вознаграждение за рекомендацию друзей в команду Сбера.
HireSeeker собирает вакансии со всех площадок и присылает только релевантные. Бесплатно.