Machine learning engineer in logistics

A Senior Machine Learning Engineer is required to design, build and optimise scalable machine learning systems within a logistics technology environment. The role focuses on developing complex ML pipelines, deploying and maintaining models in production, and managing real-time and batch inference systems. Working closely with Data Science, Data Engineering and other technical teams, you will ensure machine learning applications are reliable, efficient and scalable. You will also provide technical leadership, influence engineering best practices and help shape the long-term development of machine learning infrastructure.

• Design and oversee complex machine learning pipelines across logistics-related domains.
• Build, deploy and continuously improve data science applications and production ML models.
• Manage real-time and batch inference systems supporting predictive platforms.
• Optimise machine learning models and services for performance, reliability and scalability.
• Lead the integration of new technologies and tools into existing infrastructure.
• Establish and promote best practices across machine learning engineering and MLOps.
• Work closely with Data Science teams to support model deployment and optimisation.
• Collaborate with cross-functional teams to identify future technical requirements and implement long-term solutions.
• Provide technical leadership and communicate complex concepts to technical and non-technical stakeholders.

• Extensive experience designing, deploying and maintaining machine learning models and services in production.
• Expert-level knowledge of cloud technologies, ideally AWS.
• Strong experience with containerisation and orchestration tools, preferably Kubernetes.
• Deep understanding of software engineering, DevOps and MLOps practices.
• Strong knowledge of machine learning and experience collaborating with Data Scientists.
• Experience with MLflow for experiment tracking and model management.
• Familiarity with Airflow or Dagster for ML pipeline orchestration.
• Significant Data Engineering experience, including Kafka and stream processing technologies.
• Strong Python and SQL programming skills.
• Proven technical leadership and experience driving engineering best practices.
• Excellent communication, problem-solving and stakeholder collaboration skills.

• Full-time, Monday to Friday, 37.5 hours per week.
• This is a full-time hybrid position based in London, with three days per week in the office and two days working remotely.