Staff Data Scientist I - ETA
Careem View all jobs
- Dubai
- Permanent
- Full-time
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 RoleAs a Staff Data Scientist I - ETA, you will own the end-to-end ETA prediction systems for Careem's Food and Groceries verticals. This is a highly technical Individual Contributor role with full domain ownership across architecture, modeling strategy, experimentation, production deployment, and operational excellence.You will define the long-term vision for ETA systems in high-load, latency-sensitive marketplace environments. You will design and implement multi-stage stochastic pipelines that model preparation time, assignment delay, pickup time, travel time, batching, and pooling effects delivering reliable, calibrated predictions at scale. This role requires deep expertise in time-series forecasting, deep learning, and operations research combined with strong production experience in distributed and real-time systems. You will collaborate closely with Product, Engineering, Marketplace, and Operations leaders, ensuring ETA becomes a core competitive advantage in Careem's Everything App.What You'll Do1. ETA Vision & Architecture Ownership
- Define and own the long-term technical vision for ETA systems across Food and Groceries.
- Architect scalable, multi-stage pipelines.
- Design probabilistic and stochastic modeling approaches with uncertainty calibration and reliability guarantees.
- Establish modeling standards and best practices for ETA across the organization.
- Develop and deploy production-grade ML systems leveraging:
- Deep learning architectures
- Time-series forecasting
- Graph-based and routing-aware models
- Operations research techniques
- Build models robust to marketplace volatility and supply-demand shifts.
- Optimize for both point accuracy and distributional correctness (confidence intervals, tail control).
- Continuously improve system performance under high traffic and low-latency constraints.
- Design and deploy scalable real-time inference pipelines.
- Ensure model reliability, monitoring, alerting, and graceful degradation under load.
- Collaborate with Data Platform and ML Ops teams to productionize models using Spark, Trino, Python, and distributed frameworks.
- Lead model lifecycle management, retraining strategies, and performance tracking in live environments.
- Define clear evaluation frameworks aligned with business metrics (conversion, cancellations, fulfillment efficiency, customer trust).
- Design and run controlled experiments to measure ETA improvements and marketplace impact.
- Drive measurable improvements in operational efficiency and user experience through data-driven insights.
- Lead cross-team architectural discussions.
- Conduct design reviews and raise the technical bar for modeling quality and system robustness.
- Mentor senior data scientists and engineers in advanced ML and modeling techniques.
- Contribute to Careem's applied AI community through technical talks, documentation, and research initiatives.
- 8+ years of experience in Applied Machine Learning or Data Science, with significant experience building large-scale production systems.
- Advanced degree in Computer Science, Statistics, Engineering, Operations Research, or a related quantitative field.
- Proven expertise in:
- Time-series forecasting
- Deep learning
- Stochastic modeling
- Operations research and optimization
- Strong experience building and deploying high-load, low-latency ML systems.
- Hands-on proficiency in Python, Spark and ML frameworks.
- Experience with real-time inference systems and model monitoring in production.
- Strong understanding of experimentation, A/B testing, and causal inference.
- Demonstrated ability to drive architectural decisions across teams.
- Excellent communication skills and ability to translate complex modeling trade-offs into business impact.
- Work and learn from great minds by joining a community of inspiring colleagues.
- Put your passion to work in a purposeful organisation dedicated to creating impact in a region with a lot of untapped potential.
- Explore new opportunities to learn and grow every day.
- Work 4 days a week in office & 1 day from home, and remotely from any country in the world for 30 days a year with unlimited vacation days per year. (If you are in an individual contributor role in tech, you will have 2 office days a week and 3 to work from home.)
- Access to healthcare benefits and fitness reimbursements for health activities including gym, health club, and training classes.