Senior ML Ops Engineer — Remote, Scalable GPU Inference

Pragmatike

Italia

In loco

EUR 90.000 - 120.000

Tempo pieno

3 giorni fa

Candidati tra i primi

Ricevi più risposte dai datori di lavoro

Invia un CV specifico per questa offerta in pochi minuti.

Descrizione del lavoro

Pragmatike is seeking a skilled ML Ops Engineer to design, build and operate scalable model serving for AI workloads in a fully remote, Europe/EMEA-based role. You will collaborate with infra, platform and AI teams to ensure low latency, high availability and cost-efficient inference across distributed GPU systems.

Responsibilities include deploying robust pipelines, auto-scaling, multi-model serving, and observability.

Competenze

4+ years in ML Ops or similar infrastructure roles.
Hands-on with model serving frameworks and production systems.
Production-grade GPU workloads experience and orchestration.
Python and infra-as-code tools (Terraform/Helm).
Strong distributed systems knowledge and reliability focus.
Ability to work independently in a remote-first environment.

Mansioni

Build and operate production-grade model serving infrastructure using frameworks such as vLLM, TGI, Triton, or equivalent.
Design and implement robust deployment pipelines with blue/green and canary rollouts for ML models.
Develop and maintain auto-scaling systems, multi-model serving architectures, and intelligent request routing layers.
Optimize GPU utilization, memory efficiency, network throughput, and model artifact storage performance.
Design observability systems for tracking inference latency, throughput, GPU usage, cost metrics, and system health.
Manage model registries and CI/CD pipelines enabling automated and reproducible model deployments.
Own the full lifecycle of ML systems from development through production, including operational support and on‑call responsibilities.
Define engineering best practices and contribute to platform scalability in a fast‑moving startup environment.