Senior ML Engineer, Core DevelopmentActive$292K
The opportunity
Anduril Industries is a defense technology company with a mission to transform U. S.
What you'll do
Own the Surrogate Modeling Stack: Drive the end-to-end design, training, and deployment of production-grade surrogate models to accelerate critical simulation workflows (CFD, FEA, thermal, structural, and aeroelastic) across air vehicle design.
Develop State-of-the-Art Architectures: Design and implement neural architectures tailored to engineering physics, developing new techniques for uncertainty quantification, active learning, and inverse problems (such as geometry and shape optimization).
Build Robust Data & Training Infrastructure: Create the pipelines behind the training—extracting, aggregating, and sanitizing tens of thousands of high-fidelity results from solver outputs.
Optimize & Integrate: Optimize inference for the design loop (maximizing GPU utilization, batched evaluation, and interactive-speed latency) and seamlessly integrate surrogate predictions into the tooling our domain engineers already use.
Collaborate & Mentor: Partner with domain engineers to identify where ML delivers the highest leverage, stay current with Physics AI research, and provide technical mentorship to non ML engineers.
Education: BS, MS, or PhD in aerospace, thermal, mechanical, or electrical: engineering, or in machine learning/AI/data science with a demonstrated engineering foundation.
What they're looking for
- Experience: 3+ years of experience taking ML models from R&D into production: using large-scale scientific or engineering datasets.
- Physics ML Expertise: Working knowledge of modern surrogate architectures (e.g. GNNs, Transolver, DoMINO & GeoTransolver) combined with hands-on experience running physical simulations (CFD, FEA, thermal, etc.) and a command of the underlying numerical methods.
- Software & Frameworks: Proficiency in Python and MATLAB; experience with PyTorch, TensorFlow, and NVIDIA PhysicsNeMo (Modulus); and experience developing on Linux with GPU accelerators and distributed training.
- Data & Engineering Best Practices: Track record of building production data pipelines from heterogeneous engineering sources, utilizing uncertainty quantification, conducting statistical analysis, and building data science dashboards