Join CMG's Innovation Lab asMachine Learning Engineer with a Master's or PhD focused on Physics-Informed Neural Networks (PINNs), Fourier Neural Operators (FNOs), Deep Reinforcement Learning (DRL) for reservoir and CFD applications. In this role you'll blend advanced ML theory with practical reservoir modeling, driving accuracy and performance improvements from concept through production.Key Responsibilities Simulation & ML Integration:Design and implement PINN-based solvers, FNO surrogates or others to accelerate reservoir simulation and optimize subsurface workflows.Integrate your models into CMG's simulation pipeline, ensuring numerical stability and scientific rigor.Build scalable data pipelines for large-scale geological and production datasets.Containerize and deploy inference services, wrapping PINN/FNO models with robust APIs.Strategic Roadmap:Collaborate with domain experts to define a multi-year ML/AI strategy for reservoir simulation.Identify key research areas and drive prototyping of next-generation ML solvers.Early-Stage Research & Delivery:Lead R&D projects—from literature review and algorithm design through hands-on implementation and performance benchmarking.Validate model accuracy against high-fidelity simulators and real field dataCross-Functional Collaboration:Pair with software engineers to productionize algorithms under clean-architecture and CI/CD best practices.Present findings, trade-offs, and performance metrics to stakeholders in product and subsurface teamsThe above statements are intended only to describe the general nature of the job and should not be construed as an all-inclusive list of position responsibilities.Knowledge, Skills & Experience Academic Excellence:Master's or PhD in Computational Science, Mechanical/Reservoir Engineering, Applied Mathematics, or related field—particularly with a focus on PINNs, FNOs, or CFD.Deep ML & Scientific Computing:Proven experience implementing PINNs, FNOs, or other physics-informed architectures in TensorFlow or PyTorch.Desirable : Hands-on track record with DRL—policy-gradient (PPO, TRPO), actor-critic (SAC, DDPG), or value-based methods (DQN).Strong background in PDEs, numerical methods, and uncertainty quantification.Software & DevOps Skills:Proficiency in Python ,C++, or other suitable languages, enabling efficient integration of AI/ML models. Familiarity with containerization (Docker) and cloud deployment (AWS/GCP/Azure) is a plus.Analytical & Problem-Solving:Track record of publishing or presenting research, solving complex numerical challenges, and rigorously benchmarking solutions.Teamwork & Communication:Comfortable collaborating across disciplines—translating deep technical work into actionable product features.If you have the necessary qualifications, and are interested in a challenging career with us, please forward your resume in confidence to resumes@cmgl.ca .No phone calls please. We thank all applicants for their interest in advance. Only those chosen for interviews will be contacted.CMG Compensation and Benefits Overview Why Join Us? Competitive Package.Research Freedom: Access to HPC clusters, GPU farms, and open datasets to advance ML/RL research.High Impact: Your work will directly accelerate CMG's simulation products and shape industry-leading digital-twin and optimization technologies.Machine Learning Engineer – Agentic LLM & Workflow Automation Sharp Reflections, Sales and Account Manager – Americas Houston (with flexibility for remote work)#J-18808-Ljbffr