Research Engineer — Differentiable Optimization

Turn fast physics predictions into design optimization tools that explore engineering tradeoffs and verify promising candidate geometries.

• Develop gradient-based, constrained, and multi-objective engineering optimization.
• Integrate neural surrogate models into automated search loops.
• Build differentiable geometry parameterizations.
• Optimize aerodynamic performance under realistic constraints.
• Validate optimized candidates against high-fidelity CFD.
• Study uncertainty-aware optimization strategies.
• Compare efficiency and design quality to established baselines.

• Strong numerical optimization and applied mathematics.
• Python with PyTorch, JAX, or comparable differentiable programming.
• Gradient-based, constrained, or multi-objective optimization.
• Familiarity with numerical simulation and surrogate modeling.
• Ability to build reproducible research software.

• Aerodynamic shape or multidisciplinary design optimization.
• Adjoint methods, Bayesian optimization, or evolutionary methods.
• OpenMDAO, SciPy optimization, CAD parameterization, CFD.

Deliver a workflow that discovers verified engineering designs more efficiently than conventional baselines.

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