Description
No description provided.
Responsibilities
•Design, develop, and deploy scalable machine learning systems that power demand forecasting and related AI products.
•Design and maintain reliable ML workflows across the model lifecycle, including data preparation, experimentation, training, evaluation, deployment, inference, monitoring, and continuous improvement.
•Build and optimise large-scale data processing and feature engineering pipelines using technologies such as PySpark and Databricks, enabling efficient preparation of training and inference datasets.
•Develop multimodal machine learning solutions that combine diverse data sources, including product images, text, structured metadata, and behavioural signals, to create rich representations for downstream AI applications.
•Train and productionise deep learning models using modern architectures such as Transformers, foundation models, and other representation learning approaches.
•Partner with Applied Scientists to translate new modelling approaches into reliable, scalable production systems.
•Improve the performance, reliability, scalability, and observability of ML systems operating in production.
•Drive engineering excellence through architecture discussions, code reviews, mentoring, and knowledge sharing.
Requirements
•Significant experience designing and deploying machine learning systems in production environments.
•Strong software engineering skills in Python, with experience building maintainable, tested, and production-quality code.
•Strong experience with large-scale data processing using technologies such as PySpark and Databricks.
•Experience designing and building ML pipelines across the full lifecycle, from data preparation and model development through to deployment and monitoring.
•Experience developing deep learning models using frameworks such as PyTorch, TensorFlow, or similar.
•Experience with multimodal machine learning, representation learning, or embedding models, combining data sources such as images, text, structured metadata, or behavioural signals.
•Strong understanding of modern deep learning architectures, particularly Transformers, foundation models, multimodal learning, and representation learning techniques.
•Experience working with distributed computing, large datasets, and scalable model training or inference systems.
•Familiarity with cloud platforms and modern MLOps practices.
•Strong communication skills and the ability to collaborate effectively with scientists and engineers.
•A pragmatic mindset, balancing technical excellence with delivering business value.
Conditions
No conditions stated in the posting.
