Job Description
This company is looking for an AI/ML Infrastructure Engineer to help optimize large scale training and inference workloads across next generation GPU environments. The role sits at the intersection of AI infrastructure, platform engineering and customer facing optimization work, supporting some of the most advanced AI workloads running in Europe.
Responsibilities
- Work closely with AI/ML customers to optimise large scale training and inference workloads.
- Support deployment, troubleshooting and performance tuning across GPU heavy AI environments.
- Build and improve internal ML platforms running on Kubernetes.
- Support job scheduling, workflow orchestration and distributed training infrastructure.
- Improve inference platforms including model packaging, serving frameworks and latency optimisation.
- Optimise GPU utilisation, networking and overall workload efficiency.
- Support technologies such as vLLM, Ten...