Описание
The client is a global consultancy whose client focuses on building Kubernetes-based ML infrastructure for production model-serving components.
Задачи
- Build Kubernetes-based ML infrastructure for production model-serving components
- Build and operate Kubernetes-based ML infrastructure, preferably on AWS/EKS
- Manage GPU workloads and production ML model serving for low-latency and high-throughput inference
- Develop deployment pipelines
- Monitor, troubleshoot, and tune performance
- Operate scalable ML platforms
Требования
- Strong hands-on experience building and operating Kubernetes-based ML infrastructure
- Expertise in GPU workloads and production model serving
- Experience with low-latency and high-throughput inference
- Experience productionizing ML models, deployment pipelines, monitoring, troubleshooting, performance tuning, and scalable ML platform operations
- Must have the right to work in Europe without needing visa sponsorship
- Nice to have: AWS/EKS, NVIDIA Triton
Условия
- Paying up to €520 per day
- Initial contract until the end of the year with a high likelihood of extension
- Must have the right to work in Europe without needing visa sponsorship