What you’ll be doing
Model Development:
Design, train, and optimise machine learning models for user personalisation, including recommendation systems, ranking models, user segmentation, and content understanding, with a strong focus on TensorFlow-based development.
Data Pipeline Engineering:
Build and maintain scalable data pipelines to support feature engineering and model training across large structured and unstructured datasets, leveraging cloud‑native tooling.
Production Deployment:
Deploy, monitor, and maintain ML models in production environments, including cloud‑based model serving on GCP. Ensure high availability, strong performance, and continuous model relevance.
Experimentation:
Lead A/B testing and offline experimentation to evaluate model performance and guide ongoing improvement.
Cross‑Functional Collaboration:
Work closely with engineering, product, data, and research teams to ensure ML solutions align with product and business goals.
Research & Innovation:
Stay informed on advances in machine learning, deep learning, and personalisation, and evaluate their integration into existing systems.
What you'll bring
* End‑to‑end experience across the ML lifecycle: model development, training, deployment, monitoring, and continuous maintenance.
* Strong proficiency in Python and ML frameworks, with expertise in TensorFlow (and experience with PyTorch).
* Experience with GCP machine learning and data services (e.g., Vertex AI, Dataflow, BigQuery, AI Platform, Pub/Sub).
* Hands‑on experience with ML training frameworks such as TFX or Kubeflow Pipelines, and model‑serving technologies like TensorFlow Serving, Triton, or TorchServe.
* Background working with large‑scale batch and real‑time data processing systems.
* Strong understanding of recommender systems, ranking models, and personalisation algorithms.
* Familiarity with Generative AI and its use in production environments.
* Strong communication skills and analytical problem‑solving abilities.