Palk täpsustamataTuruvahemik: 4150–5700 €
Responsibilities
Building and operating production-grade ML inference infrastructure, including model serving with frameworks like vLLM and Triton, deployment pipelines, auto-scaling, GPU optimization, observability, and full lifecycle management.
Requirements
- ML Ops experience (4+ years)
- Model serving frameworks (vLLM, TGI, Triton)
- Container orchestration & GPU workloads
- Python
- Infrastructure-as-code (Terraform, Helm)