About the role
Pragmatike is recruiting for a distributed cloud infrastructure startup building GPU-powered services for AI and machine learning workloads. The ML Ops Engineer will build and operate production model-serving infrastructure for real-time applications, collaborating with infrastructure, platform, and applied AI teams. The listing describes a hands-on role with ownership across the ML systems lifecycle, from development through deployment and operational support.
The work includes serving frameworks such as vLLM, TGI, or Triton; deployment pipelines with rollout strategies; autoscaling and request routing; and observability for latency, throughput, GPU use, and cost. Applicants need at least four years in ML Ops, platform engineering, SRE, or similar infrastructure work focused on ML systems, plus production GPU workload experience and Python. The role is fully remote in the EMEA timezone.
Highlights
- Build and operate production ML inference infrastructure.
- Work on GPU utilization, autoscaling, routing, and reliability.
- Own model deployment pipelines and operational support.
- Requires 4+ years in relevant ML systems infrastructure roles.
This recap is dataskew's editorial summary, not the company's copy.