Machine Learning Engineer

Tamara; Dubai; On-site; AED 300,000 - 400,000; Full time

Job summary

A leading fintech platform in Dubai is searching for a Senior Machine Learning Engineer to design, build, and deploy machine learning models for credit risk and fraud prevention. The ideal candidate will have over 6 years of experience, strong Python skills, and a solid understanding of cloud-based model deployment. This role includes responsibilities such as building CI/CD pipelines and integrating models with existing systems. Competitive compensation offered.

Qualifications

• 6+ years of experience as an MLE or similar role.
• Proficiency in deploying ML models in cloud environments.
• Strong understanding of containerization and orchestration.

Responsibilities

• Develop and deploy risk and fraud models in production.
• Build CI/CD pipelines for model monitoring.
• Integrate ML models with critical business systems.

Skills

Strong Python skills

Experience with MLOps tools

Proficiency in distributed computing frameworks

Solid knowledge of microservice architecture

Experience in building and integrating with real-time streaming systems

Tools

Python (Pandas, NumPy, scikit-learn)

FastAPI/Flask

Spark

Ray

Airflow

Docker

Kubernetes

Kafka

Job description

About Us

Tamara is the leading fintech platform in Saudi Arabia and the wider GCC region with a mission to help people make their dreams come true by building the most customer-centric financial super-app on earth. The company serves millions of users in the region and partners with leading global and regional brands such as SHEIN, Jarir, noon, IKEA and Amazon, as well as small and medium businesses.

Tamara is Saudi Arabia’s first fintech unicorn and is backed by Sanabil Investments, a wholly owned company by the Public Investment Fund (PIF), SNB Capital, Checkout.com, amongst others. The company operates from its headquarters in Riyadh, with additional regional and global support offices.

Your Role

We are looking for a Senior Machine Learning Engineer (MLE) to join our Risk Data Science team. You will play a key role in designing, building, deploying, and scaling ML models that drive credit risk, fraud prevention, behavioral scoring, and other risk-related decision systems across our business.

You will work closely with data scientists, risk analysts, and engineering teams to transform research prototypes into high-performance, production-grade solutions that operate at scale in real-time decisioning environments.

Your Responsibilities

Model Deployment & Scaling

• Productionise risk and fraud models developed by the DS team using robust, efficient, and maintainable architectures
• Design low-latency, high-availability APIs and pipelines for real-time model inference.
• Implement batch scoring systems for periodic risk assessments.

MLOps & Infrastructure

• Build and maintain CI/CD pipelines for model deployment and monitoring.
• Set up automated feature engineering pipelines, leveraging feature stores.
• Ensure model governance: reproducibility, versioning, auditability, and compliance with regulatory requirements.

Model Monitoring & Maintenance

• Implement real-time and batch monitoring for data drift, concept drift, and model performance.
• Build automated retraining workflows and model rollback mechanisms.

Collaboration with Risk DS

• Work closely with risk data scientists to translate experimental code (Python, notebooks) into production-grade services.
• Advise DS on efficient model architectures for operational environments.
• Optimize feature computation for speed and scalability.

System Design & Integration

• Integrate models with credit underwriting, fraud detection, collections, and merchant risk systems.
• Collaborate with backend engineering to align on API contracts and system interfaces.

Your Expertise

• 6+ years of experience as an MLE, ML Engineer, Mlops Developer.
• Strong Python skills (including Pandas, NumPy, scikit-learn, PySpark, FastAPI/Flask).
• Proficiency in distributed computing frameworks (Spark, Ray) and workflow orchestration tools (Airflow, Prefect).
• Experience with MLOps tools (MLflow, SageMaker, Vertex AI, or similar).
• Strong understanding of model deployment in cloud environments (AWS/GCP/Azure).
• Solid knowledge of microservice architecture, containerization (Docker), and orchestration (Kubernetes).
• Proven track record of deploying and maintaining ML models in production at scale.
• Experience in building and integrating with real-time streaming systems (Kafka, Kinesis, Pub/Sub).

All qualified individuals are encouraged to apply.