Software Engineer, Engineering Simulation & Automation (Vehicle Engineering)

Responsibilities

• Develop and maintain automated simulation pipelines that generate training datasets for AI surrogate models at scale
• Partner with domain engineers to identify bottlenecks and build custom tools that improve productivity and reduce manual effort
• Create and optimize scripts using APIs such as ANSA Python API, Star-CCM+ Java/Python macros, OpenTD, Abaqus, or equivalent tools
• Build parametric workflows for geometry variation, automated meshing, batch simulation execution, and result extraction
• Orchestrate large-scale simulation campaigns on HPC clusters using job schedulers and workflow managers
• Collaborate closely with ML engineers to understand dataset requirements and iteratively improve data quality and diversity
• Implement data management, cleaning, metadata tagging, and versioned storage of simulation results
• Develop general automation tools and scripts to accelerate engineering workflows across simulation, analysis, design, and testing tasks
• Deep dive into engineering physics domains to ensure simulation setups are accurate, robust, and efficient for surrogate training
• Integrate simulation tools with version control, CI/CD pipelines, and monitoring systems for reproducible datasets
• Stay current with advances in simulation automation, meshing technology, and best practices for ML-ready datasets

BASIC QUALIFICATIONS

• Bachelor’s degree in engineering, computer science, data science, math, physics, or a related technical discipline; OR 4+ years of professional experience building software or simulation pipelines in lieu of a degree
• 1+ years of software development experience
• 1+ years of hands-on experience with at least one simulation domain (CFD, FEA, thermal, structural analysis, etc.)

PREFERRED SKILLS

• Experience with ANSA, Star-CCM+, OpenFOAM, Abaqus, OpenTD, OpenFOAM, CalculiX or similar commercial/in-house/open source simulation tools
• Strong proficiency scripting simulation APIs (especially ANSA Python API or Star-CCM+ automation)
• Demonstrated success building automated workflows that run thousands of simulations for dataset generation
• Understanding of Design of Experiments (DOE) and sampling techniques such as Latin Hypercube (LHS)
• Experience working in HPC environments with job schedulers such as Slurm or equivalent
• Familiarity with surrogate modeling concepts and the data requirements of neural operators, FNOs, physics-informed ML, or similar models
• Familiarity with deep learning and preparing data for ML workflows
• Proficiency with Python for scientific computing and automation
• Experience developing on Linux systems
• Strong understanding of version control, testing, continuous integration, build, deployment, and monitoring
• Good understanding of statistics, numerical methods, and core engineering simulation techniques