Gett is a Ground Transportation Solution with the mission to organize all the best mobility providers in one global platform - optimizing the entire experience from booking and riding to invoicing and analytics, to save businesses time and money. We work with a third of the Fortune 500 companies and have over 17K active business customers across the world.

We are looking for a Backend Engineer to join our Data Science team.

Our group tackles complex challenges requiring innovative solutions across algorithms, machine learning models, and LLMs.

In this role, you will partner directly with Data Scientists to transition research prototypes into efficient, production-ready microservices. You will collaborate with a broad forum of experts including architects, data engineers, and product managers, to deliver high-quality technical solutions that drive our product forward.

Responsibilities

• Model Tech-Transfer: Transition research prototypes (from Data Scientists) into efficient, production-ready microservices
• Pipeline Management: Build and maintain automated pipelines for data collection, model training, and deployment (using Jenkins & Airflow)
• Infrastructure Ownership: Deploy, tune, and manage AWS cloud resources (EC2, S3, ElastiCache) for low latency and high availability
• Monitoring and Evaluation: Implement monitoring for model performance (accuracy, statistical calibration) and Business Performance (adherence with company KPI, business impact)
• Quality Assurance: Write robust unit tests and optimise code for performance

Requirements

• Backend Engineering: 2+ years of Python and SQL development experience. Proven ability to design and build components for a microservices architecture, write high-performance code, and utilize numerical computing libraries (e.g., NumPy).
• MLOps: Proven experience operationalizing machine learning models, including building automated training and inference pipelines, model deployment, and monitoring models in production.
• System Design: Extensive, hands-on experience designing, building, and optimizing scalable systems for high-traffic, low-latency environments.
• Cloud & DevOps: Experience working with containerization (Docker) and CI/CD pipelines (e.g., Jenkins).
• Cross-Functional Collaboration: Strong ability to translate abstract research concepts and product requirements into clear, actionable technical specifications.
• Advantage: Hands-on experience with data orchestration tools, particularly Apache Airflow.