Develop feature engineering pipelines and index construction systems supporting e-commerce recommendation model training and search relevance optimization
Model Lifecycle and Drift Control:Build and operate the deployment path, including real-time and batch inference, result storage, performance monitoring, drift detection, retraining triggers, feature change management, and rollback, ensuring training and production feature pipelines are provably identical.
4+ years as a software engineer, data engineer, or AI/ML practitioner writing technical design documents, data pipeline documentation, or API specifications
Optimise system and pipeline performance through ongoing monitoring and implementation of scalable solutions designed to handle expanding data volumes and growing organisational demands.
Design data models for mission-critical, high-volume, near-real-time/batch data; build idempotent/atomic production data pipelines to make data ingestion more fault tolerant.
World-class benefits: On top of a competitive salary (based on your location, experience, and skills), we provide a comprehensive benefits package to enable holistic well-being for you and your family.
Pipeline Architecture: Design, build, and maintain robust, highly scalable ETL/ELT data pipelines to ingest and process vast amounts of data from diverse sources.
Design and operate production-grade pipelines across statistical, licensed, API, database, file and web sources, with robust validation, monitoring and recovery.