What are the responsibilities and job description for the Senior Surrogate & Simulator Modeler position at Grafton Sciences?
About Grafton Sciences
We’re building physical general intelligence — autonomous systems that can experiment, reason, and discover in the physical world. With deep technical roots and real-world progress at scale (e.g., a $42M NIH project), we’re pushing the frontier of physical AI. Joining us means inventing from first principles, owning real systems end-to-end, and helping build a capability the world has never had before.
About The Role
We’re seeking a Senior Surrogate & Simulator Modeler to create high-fidelity, multi-scale surrogate models and fast physics approximators that power optimization, digital twins, and RL systems. You’ll build multi-fidelity models, uncertainty-aware predictors, operator-learned physics kernels, and accelerated simulation layers across electromagnetics, thermal, mechanical, and process domains. This role is ideal for someone who blends physics intuition with statistical modeling and can make large, complex simulations tractable for real-time decision-making.
Responsibilities
Compensation
We offer competitive salary, meaningful equity, and benefits.
We’re building physical general intelligence — autonomous systems that can experiment, reason, and discover in the physical world. With deep technical roots and real-world progress at scale (e.g., a $42M NIH project), we’re pushing the frontier of physical AI. Joining us means inventing from first principles, owning real systems end-to-end, and helping build a capability the world has never had before.
About The Role
We’re seeking a Senior Surrogate & Simulator Modeler to create high-fidelity, multi-scale surrogate models and fast physics approximators that power optimization, digital twins, and RL systems. You’ll build multi-fidelity models, uncertainty-aware predictors, operator-learned physics kernels, and accelerated simulation layers across electromagnetics, thermal, mechanical, and process domains. This role is ideal for someone who blends physics intuition with statistical modeling and can make large, complex simulations tractable for real-time decision-making.
Responsibilities
- Develop surrogate models, reduced-order models, and multi-fidelity approximations grounded in real physics and simulation data.
- Build uncertainty-aware predictors, stability mechanisms, and domain-specific physics kernels for use in optimization and RL loops.
- Implement model-based optimization techniques (MOBO, SafeOpt, Pareto modeling) for complex engineering workflows.
- Collaborate with simulation, digital twin, RL, and agent teams to integrate surrogate models into high-throughput learning and decision pipelines.
- Strong experience building surrogate models, reduced-order physics models, or multi-fidelity simulation approximations.
- Familiarity with uncertainty estimation, optimization under constraints, and physics-informed modeling techniques.
- Ability to translate full-scale simulation outputs into efficient, learnable models that preserve fidelity and stability.
- Comfortable working across ML, simulation tools, and domain-specific physics in a fast-moving, interdisciplinary environment.
Compensation
We offer competitive salary, meaningful equity, and benefits.
