Senior MLOps Engineer

TL;DR

Senior MLOps Engineer (MLOps/GCP): Build and industrialize the MLOps infrastructure for production shipping of ML models with an accent on ML CI/CD, model monitoring and troubleshooting directly in production, and large-scale reproducible experimentation. Focus on connecting ML and platform teams, delivering MLOps building blocks (MLflow, Kubeflow, KubeRay), and managing GPU infrastructure scarcity while running on-call responsibilities.

Location: Full Remote from France

Salary: EUR 75,000–85,000 yearly

Company

hirify.global builds video and advertising products powered by an AI-first approach.

What you will do

• Empower ML engineers with tools, infrastructure, and frameworks to iterate autonomously and faster.
• Accelerate time-to-market for production ML products through seamless integrations, proper service connections, and access to data/resources.
• Own ML CI/CD by adapting existing frameworks to ML-specific needs.
• Keep models under control in production: monitor, troubleshoot, and iterate directly in prod (no staging/prod mirror).
• Enable large-scale ML experimentation with robust, reproducible, scalable environments for internal tests and A/B testing.
• Deliver MLOps building blocks (MLflow, Kubeflow, KubeRay) and manage GPU infrastructure dynamically; handle run responsibilities (on-call, post-mortems, L1 failure analysis).

Requirements

• Strong MLOps or DevOps background with shipped production projects.
• Expertise in GCP: Vertex AI, GKE, GCS, BigQuery.
• Full GitOps experience (FluxCD preferred; ArgoCD accepted) and Kubernetes in production.
• Hands-on with real MLOps tools: MLflow, Kubeflow, KubeRay.
• GPU-aware experience managing GPU scarcity at scale during large training runs.
• Fluent in French and English.

Nice to have

• Jupyter Notebooks and broader ML/AI ecosystem experience.
• Data pipelines (Airflow, Dataflow, Kestra).
• Redis clusters and infrastructure performance optimization.

Culture & Benefits

• Run culture with on-call, post-mortems, and continuous improvement.
• AI-first environment where shipping models reliably is the core business.
• Collaboration across ML and platform/backbone teams with a focus on bridging and practical solutions.
• Permanent full-time role with yearly compensation in EUR.

Hiring process

• HR interview (30 min), then manager interview (1 h).
• Technical interview with 2 architects (1 h) with no coding test.
• ML interview (1 h) and final interview with VP Platform (1 h).