HPC & Scientific Data Engineer

Build and operate the compute and data workflows that generate trustworthy simulation datasets for training physics foundation models.

• Design scalable CFD data-generation pipelines.
• Orchestrate large simulation batches on CPU/GPU clusters.
• Automate geometry preparation, meshing, solver execution, post-processing, and storage.
• Implement monitoring, checkpoints, retry, and recovery.
• Check solver convergence, physical consistency, and dataset completeness.
• Maintain reproducible metadata, versioning, and provenance.
• Optimize compute utilization and data throughput.

• Strong Python engineering.
• HPC, distributed systems, or large-scale scientific workloads.
• Linux, containers, and job orchestration.
• Scientific data pipelines, storage, and automation.
• System reliability and debugging skills.

• Slurm, Kubernetes, Ray, MPI, or CUDA.
• OpenFOAM and automated CFD workflows.
• HDF5, Zarr, Parquet, large scientific datasets.
• GPU-cluster optimization.

Produce high-quality physics datasets reproducibly at scale, with low wasted compute and visible failure rates.

Send your CV and a relevant paper, technical project, GitHub repository, or portfolio to careers@ratiolabs.ai. Suggested email subject: “Data Generation”.