Godela

Compensation

Full Description

At Godela, we're building the first Physics Foundation Model; a physics-informed AI platform learns from simulation, experiment, and equations to instantly predict and simulate physical behavior. At Godela, our vision is to push the boundaries of scientific discovery and engineering innovation. We’re scaling deep-learning surrogates so every engineer has the power of an R&D lab at their fingertips to turn months of simulation and experimentation into minutes. Founding Simulation Engineer We are seeking a Founding Simulation & Data Engineer to help us build and scale the world's first Physics Foundation Model. This role is a strategic pillar, focusing on defining the data engine and validation strategy required to ensure our models accurately capture the complex physical world. What you’ll do Define the methodology for representing physical systems in data and models—balancing accuracy, scale, and generalization. Own the strategy for validating and verifying our model outputs against ground-truth simulation and experimental data. Generate and curate simulation data across multiple physics domains (CFD, FEA, multiphysics), ensuring high-fidelity coverage of complex behaviors. Build scalable pipelines and standards for turning simulation and experimental data into training-ready datasets. Drive the research and engineering of novel techniques for data augmentation, curation, and generation Collaborate with ML researchers to integrate new architectures, ensuring data and models align with physical truth. Work directly with the founders to set strategy: which physical behaviors to target, how to represent them, and how to scale methods across domains. What We're Looking For Hands-on CAD generation and Simulation Expertise: Deep experience with one or more simulation domains (e.g., CFD, FEM, DEM) and commercial or open-source solvers (e.g., Star-CCM+, Fenics/dolfinx, OpenFOAM). Robust Programming Skills: Strong proficiency in Python is a must. Experience with C++ or other compiled languages for performance-critical tasks is a big plus. Data Pipelining Experience: Proven track record of building and managing data pipelines for large datasets, preferably in a scientific or engineering context. Problem-Solving Mentality: A demonstrated ability to creatively solve complex, unstructured problems. Nice-to-haves: Solver development experience Familiarity with ML frameworks like PyTorch, JAX, or TensorFlow. Experience with parallel and distributed computing for simulation or data processing. Experience with Graph Neural Networks, Physics-Informed Neural Networks, Neural Operators, and Transformer architectures System-Level Thinking: Experience with cloud computing platforms (AWS, GCP, or Azure) and high-performance computing (HPC) environments (Slurm, PBS).