Senior Machine Learning Engineer (Inference)

This role is with a rapidly expanding AI infrastructure company that aims to make cloud-native AI systems more autonomous and efficient. Rather than simply monitoring systems, their platform actively adapts and optimises infrastructure in real time so large organisations can run demanding ML workloads with minimal human oversight.

This is an R&D-heavy position rather than a maintenance job. You'll tackle greenfield challenges in scaling AI systems, including boosting inference efficiency and designing improved methods for routing and executing workloads across distributed environments. Responsibilities span model performance through to large-scale cost optimisation.

The tech stack centres on Python and popular ML frameworks, combined with high-throughput data systems and cloud-native tooling. It operates across multiple cloud providers and is deeply integrated with Kubernetes.

We're looking for candidates experienced with ML or data systems, especially those who have improved inference performance through optimisation, resource efficiency, or system-level tuning — people who have spent time in the trenches of ML or data systems.