Machine Learning Engineer

Project description

We are seeking a skilled and domain-expert Machine Learning Engineer to develop and deploy data-driven solutions in the context of Digital Oilfield (DOF) systems. The ideal candidate will have a strong foundation in machine learning, model development, and data analytics, with the ability to apply these skills to subsurface and production engineering workflows.

This is a hands-on technical role focused on building ML models that enhance forecasting, optimization, and operational decision-making across complex oilfield environments. Experience with agent-based or generative AI systems is a bonus, but not a requirement.

Responsibilities

Develop and maintain machine learning models tailored to oilfield data and engineering processes.

Work closely with domain experts to understand workflows and identify ML opportunities across production, reservoir, and facility systems.

Build, train, and deploy models for time series prediction, classification, anomaly detection, or clustering using structured and semi-structured data.

Validate model accuracy and performance in real-world operational settings.

Collaborate with software teams to integrate models into DOF platforms or dashboards.

(Optional but valued) Explore the use of LLMs or agentic AI to support technical queries or enhance interaction with data systems.

business trip to Kuwait

Skills

Must have

Strong background in machine learning, data modeling, and applied statistics.

Proficiency in Python and ML libraries such as scikit-learn, XGBoost, TensorFlow, or PyTorch.

Familiarity with oilfield datasets, including production data, sensor logs, simulation outputs, or engineering inputs.

Understanding of the challenges and context of oil & gas workflows, even if not from direct experience.

Ability to collaborate with geoscientists, production engineers, or field operations teams to co-design effective models.

Nice to have

Experience working with or developing for Digital Oilfield systems (DOF platforms, custom solutions, or commercial tools).

Exposure to cloud platforms such as Azure (preferred) or AWS.

Familiarity with Agentic AI frameworks (LangChain, CrewAI, AutoGen), or LLMs as a support layer in technical environments.

Knowledge of MLOps practices or tools (e.g., MLflow, Airflow, or model deployment pipelines).

Certifications :

Azure Data Engineer or AI Engineer certifications are a plus, especially for roles involving cloud-based deployment.

AWS experience is appreciated but not mandatory