MLOps Engineer

Description

The company is a global partner for AI-first digital transformation and engineering, with over 25 years of experience, around 5,000 people and presence in 16 countries.

It works across artificial intelligence, data and cloud, intelligent automation and digital products, with a focus on engineering depth.

The CEE unit has close to 1,000 specialists building applications, data platforms and AI solutions on AWS, Azure, GCP, Databricks and Snowflake.

This role sits in the Data Infrastructure team, which runs the company-wide GCP data and ML platform.

Responsibilities

• Own the ML platform infrastructure of the company-wide GCP data and ML platform as part of the Data Infrastructure team.
• Run Vertex AI, Kubeflow Pipelines and GKE-based training and serving so they stay reliable, secure and cost-efficient.
• Build templates, CI/CD pipelines and self-service workflows so data scientists can deploy models without raising tickets.
• Manage the model lifecycle: registry, versioning, deployment, rollback, and monitoring for drift and serving health.
• Support feature and training data flows across BigQuery and Airflow alongside data platform engineers.
• Manage infrastructure through GitOps with Config Sync, enforcing least-privilege access for PII and policy-tagged data.
• Manage GPU and compute usage, quotas and per-team spend visibility.
• Take end-to-end ownership of the platform that vertical teams use to build, train and serve their models.

Requirements

• At least 5 years in MLOps, ML platform or platform engineering, with a minimum of 2 years running production ML infrastructure end to end.
• Production use of GCP, mainly Vertex AI, GKE and BigQuery.
• Confident Kubernetes skills, including debugging clusters without help.
• Experience orchestrating pipelines with Kubeflow Pipelines or Vertex AI Pipelines, and with Airflow.
• Knowledge of GitOps for infrastructure (Config Sync or similar) and of CI/CD for shipping models.
• Strong production Python, covering tests and packaging.
• A platform approach: you have built documented, self-service tools for other teams, measured against SLOs.
• Able to work alone as the sole owner of a company-wide platform.
• Streaming features or online inference with Dataflow or Flink, and Kafka.
• Feature stores such as Vertex AI Feature Store or Feast, and model monitoring tools.
• LLM serving and evaluation on Vertex AI or comparable platforms.
• GPU scheduling and cost work on GKE.
• Data governance work with DataHub or policy tags, and knowledge of GDPR or DPDP.
• Background in high-scale consumer products.

Conditions

Work from the European Union; a work permit is required.

Hiring steps: CV review, HR call, interview, client interview, then decision.