Machine Learning Engineer

Eice Technology

We are seeking a skilled Machine Learning Engineer to develop and deploy Graph Neural Network (GNN)-based surrogate models that approximate complex physics simulations for oil & gas pipeline and well networks.

This is a hands-on role for an engineer who can build high-fidelity neural network models to replace computationally expensive reservoir and network simulators (Nexus, Prosper).

Key Responsibilities:

• Design and implement Neural Network architectures to model flow dynamics in interconnected pipeline networks.
• Build surrogate models to predict pressure distributions, flow rates, and network behavior under varying operational scenarios.
• Create data pipelines to extract and transform network topology and simulation results into graph representations.
• Develop training frameworks that integrate physics constraints (e.g., conservation laws, pressure-flow relationships) into neural network loss functions.
• Collaborate with petroleum engineers to ensure model accuracy and physical alignment.
• Implement model monitoring, validation, and continuous improvement workflows.

Required Skills and Experience:

• Expertise in Graph Neural Networks (GCN, GraphSAGE, Message Passing Networks) with proven implementation experience.
• Strong hands-on experience with PyTorch Geometric, DGL, or TensorFlow GNN.
• Experience building surrogate models or physics-informed neural networks (PINNs).
• Proficiency in Python, NumPy, SciPy, and Pandas.
• Ability to handle complex data structures (graphs, time-series, spatial data).
• Strong grasp of optimization techniques and large-scale training data handling.

Technical Domain Knowledge:

• Knowledge of graph theory and network analysis.
• Experience with graph data structures (adjacency matrices, edge lists, sparse tensors).
• Understanding of hyperparameter tuning, model validation, and uncertainty quantification in ML models.

Nice to Have:

• Background in petroleum engineering, process engineering, or fluid dynamics.
• Familiarity with reservoir simulation or pipeline hydraulics.
• Experience with MLOps and model lifecycle management.
• Publications or open-source contributions in Graph ML.
• Experience deploying ML models in cloud environments (Docker, Kubernetes, API development).

Industry Experience:

• Oil & Gas industry experience is a strong plus.
• Candidates with relevant surrogate modeling experience from other engineering domains are encouraged to apply.

Educational Background:

• MS/PhD in Computer Science, Computational Engineering, Applied Mathematics, or a related field preferred.
• Strong foundation in linear algebra, graph theory, and numerical methods.