Senior MLOps Engineer

About the role

The energy transition is accelerating, and data is the force behind it. Our client manages significant data volumes and is rapidly expanding its data science initiatives. To support this growth, they are constructing a modern MLOps platform on Azure. They are currently strengthening their team by seeking a Senior MLOps Engineer to drive platform development. In this position, you will own the design, construction, and enhancement of the MLOps infrastructure. Your primary mission is to enable efficient and reliable deployment of data science models into production. You will establish the foundational platform on Azure Databricks, creating automated pipelines and model registry capabilities. MLflow will be central to your model management strategy. You will also introduce robust CI/CD practices using Azure DevOps to ensure strict version control for code, models, and datasets.

A core part of your responsibility involves architecting large-scale forecasting workflows. These will be executed on Databricks Jobs, orchestrated by Apache Airflow, with comprehensive tracking provided by MLflow. You will oversee these pipelines to ensure stability and performance. As the engagement develops, your focus will shift toward knowledge transfer. You will coach the existing engineering team, empowering them to maintain and evolve the platform independently. Your legacy will be a team that is self-sufficient and capable of sustaining your improvements.

Key facts

What you'll do

You will establish the structure for CI/CD in machine learning through Azure DevOps, ensuring proper versioning of all artifacts. You will architect large-scale forecasting workflows on Databricks Jobs, managed via Apache Airflow, with MLflow used for comprehensive model tracking. You will guide data scientists to ensure smooth production rollouts and stable deployment patterns within the MLOps platform. This includes building the MLOps foundation on Azure Databricks, focusing on automated pipelines and model registry features. You will introduce monitoring and reliability practices so that deployed models behave predictably at scale. You will organize the intake of requirements and translate data science needs into concrete pipeline contracts. You will partner with analytics and business teams to ensure solutions remain aligned with evolving use cases and quality standards. You will implement logging and tracing mechanisms to support rapid diagnosis of issues in production environments. You will optimize resource utilization on the Azure platform to control costs and maintain performance targets. You will document architectural decisions and operational procedures to ensure clarity for future maintenance. You will participate in code reviews to uphold quality standards across the MLOps implementation. You will evaluate new tools and techniques to continuously improve the efficiency of the data science workflow.

Requirements

• A completed HBO or WO degree (Bachelor's or Master's).
• Proven experience as a tech lead, with the ability to guide and enable engineering teams.
• At least five years of professional experience in machine learning product development within an MLOps context. This includes data preparation, model training, deployment, and monitoring.
• Demonstrated expertise in designing and expanding MLOps infrastructure within complex organizational environments.
• Excellent Python proficiency and a strong grasp of solid software design principles, including object-oriented programming and design patterns.
• Experience building and maintaining MLOps or data platforms is essential. Prior experience with Azure Databricks is highly valued.
• A deep understanding of the requirements for deploying ML solutions at scale, reliably and securely.
• Proficiency with Infrastructure-as-Code practices, such as Terraform, is required.
• Availability to work full-time from the start date of 05/01/2026 until the end date of 04/01/2027.

Nice to have

Experience with the current tech stack is advantageous. This includes Apache Spark, Azure Databricks, MLflow, Apache Airflow, Azure DevOps, and data lineage or versioning tools.

Practical notes

Please What you'll do