The Machine Learning Engineer partners with the Solutions Architect to bring Geminus AI solutions to life. The ML engineer focuses on developing, optimizing, and deploying ML models and numerical optimizers that power Geminus’ real-time decision-making solutions.
This role bridges research, engineering, and deployment, transforming prototype models and optimizers into reliable, scalable components within customer and cloud environments.
• Design, refactor and optimize ML models into robust, maintainable production code.
• Develop and maintain training pipelines, versioning, and deployment workflows for large-scale model ensembles.
• Collaborate with Solutions Architects to define data, simulation, and model integration requirements.
• Implement and test physics-informed and hybrid ML models using TensorFlow, PyTorch, or similar frameworks.
• Manage model performance and optimization for real-time decision-making and scalability.
• Work with software engineers to deploy ML services on the Geminus platform using containerized or distributed systems.
• Conduct validation and benchmarking against customer data and simulation results.
• Contribute to automation, monitoring, and maintenance of deployed ML systems.
• 3+ years of ML engineering experience, preferably in a production setting.
• Expertise in Python, TensorFlow or PyTorch, NumPy/SciPy, and FastAPI.
• Experience building and managing ML pipelines using CI/CD, Git, and Docker.
• Strong understanding of neural networks, optimization algorithms, and model performance tuning.
• Familiarity with physics-informed ML, surrogate modeling, or simulation-based learning.
• Demonstrated ability to deploy and manage ML models at scale.
• Strong collaboration and problem-solving skills across interdisciplinary teams.
• Experience in modeling physical processes (e.g., numerical simulations, physics-informed AI, digital twins) is a plus.
Additional Notes
• U.S. work authorization required
At Geminus, you will lead the next frontier of AI adoption in the Energy industry, shaping how operations leverage real-time intelligence at scale. You’ll work with a world-class team of AI engineers, computational physicists, and industry experts, solving high-value challenges that impact the future of energy.
This role is based in the United States. As a remote-first company, Geminus allows employees to work from anywhere in the U.S. while staying connected to our office hubs in Houston, San Francisco, and Boston.
Send us your details and let’s start the conversation.
