We're partnering with an AI-first financial technology business building a next-generation digital banking platform in which artificial intelligence is at the heart of the customer experience.

As the Lead MLOps Engineer, you'll own the platform that enables AI at scale, from model deployment and inference through to GPU infrastructure, CI/CD and production reliability. This is a hands-on technical leadership role where you'll shape the architecture and engineering standards for the organisation's AI platform.

What You'll Be Doing

• Design, build and operate production ML infrastructure across cloud and on-prem environments.
• Own model deployment, serving and inference platforms for AI applications.
• Build and optimise GPU-enabled infrastructure for model training and inference.
• Develop scalable CI/CD pipelines for machine learning workloads.
• Design infrastructure using Kubernetes, Docker and Infrastructure as Code.
• Improve observability, monitoring and reliability across ML services.
• Partner closely with Data Scientists, ML Engineers and Software Engineers to productionise AI models.
• Drive automation, platform reliability and engineering best practices across the AI stack.
• Mentor engineers and provide technical leadership across the platform team.

What We're Looking For

• Strong background in MLOps, ML Platform Engineering, AI Infrastructure or Site Reliability Engineering.
• Hands-on experience with Kubernetes and containerised ML workloads.
• Experience deploying and operating machine learning models in production.
• Strong knowledge of Infrastructure as Code (Terraform, Ansible or similar).
• Experience with GPU workloads and ML inference infrastructure.
• Knowledge of CI/CD pipelines for machine learning.
• Experience with ML tooling such as MLflow, Kubeflow, SageMaker or Vertex AI.
• Strong Python skills.
• Experience building highly available, scalable distributed systems.
• Excellent communication skills with the ability to influence technical direction.