Transport AI Data Engineer - Real-Time Pipelines

Land Transport Authority (LTA) Singapore; Singapore; On-site; SGD 90,000 - 130,000; Full time

Job summary

Land Transport Authority (LTA) Singapore is hiring a Data Engineer for the Transport AI Programme to design and maintain data infrastructure that powers AI models across real‑time and batch data sources.

You will build scalable pipelines, manage data models and feature stores, ensure data quality and governance, and collaborate with AI developers, infrastructure engineers, and industry partners in a cloud/hybrid environment.

Qualifications

• 3–6 years of relevant professional experience.
• Proficient in Python and SQL, with Spark/Kafka experience.
• Experience with cloud data platforms and data warehousing.
• Experience in regulated or government environments is a plus.
• Strong communication in Agile teams.

Responsibilities

• Design, build, and maintain scalable data pipelines that ingest, transform, and serve structured and unstructured data from diverse transport data sources, including real-time streams and batch feeds.
• Develop and manage data models, data catalogues, and feature stores that support AI model training, evaluation, and inference across transport use cases.
• Ensure data quality, consistency, and lineage across the data platform, implementing validation checks, monitoring, and alerting to detect and resolve data issues early.
• Implement data governance practices in line with Singapore Government data classification requirements, including access controls, data masking, anonymisation, and audit logging for sensitive transport and personal data.
• Work with the AI Architect and Infrastructure Engineer to design data infrastructure that is performant, cost-efficient, and aligned with LTA's cloud and hybrid environment.
• Collaborate with data scientists and AI developers to understand data requirements for model development, and translate these into reliable, production-grade data products.
• Support the integration of external data sources from industry partners, ensuring that data exchange meets LTA's standards for security, quality, and interoperability.
• Contribute to the development of shared data platforms and reusable data assets that can be leveraged across multiple AI use cases within the programme.
• Monitor and maintain data pipelines in production, supporting incident response and continuous improvement of data reliability and freshness.

Skills

Python

SQL

Apache Spark

Apache Kafka

dbt

Airflow

Cloud data platforms

Data governance

ML/AI data pipelines

Data quality tooling

Metadata management

Real-time data processing

Stakeholder communication

Education

Bachelor's degree in Computer Science

Tools

AWS Glue

Azure Data Factory

Google Dataflow

Databricks

Job description

Land Transport Authority (LTA) Singapore is hiring a Data Engineer for the Transport AI Programme to design and maintain data infrastructure that powers AI models across real‑time and batch data sources.

You will build scalable pipelines, manage data models and feature stores, ensure data quality and governance, and collaborate with AI developers, infrastructure engineers, and industry partners in a cloud/hybrid environment.