About the Position

Your vision. Our solutions.

We are seeking a SRE Plattform Engineer mit MLOps to join our team in Europe. This role is remote.

Responsibilities

Designing, building, and operating a scalable internal platform for Machine Learning and AI services
Enabling reliable training, deployment, and inference of ML/AI models on our cloud-native infrastructure

Strong hands-on experience with Machine Learning and AI workloads
Extensive practical experience running ML/AI workloads on Kubernetes (production-grade)
Solid MLOps expertise, including:
- Model lifecycle management
- CI/CD for ML models
- Monitoring, logging, and reproducibility
Experience with ML and AI inference systems, focusing on scalability and low latency
Excellent knowledge of Kubernetes-based infrastructure for ML (GPU scheduling, scaling, reliability)
Experience with NVIDIA Triton Inference Server (strong plus / highly preferred)
Ability to design, build, and operate self-managed ML/AI infrastructure

The Workly s.r.o.

4D CENTER, Kodaňská 1441/46,

101 00, Praha 10.