Multiphysics & Simulation Software Engineer
Job Location:
Monthly Salary:
Experience Required:
Posted:
Application Deadline:
Vacancies:
Job Summary
The ePlane Company is at the forefront of Indias urban air mobility revolution. Incubated at IIT Madras we are a deep-tech startup dedicated to designing and building the worlds most compact electric flying taxi. Our mission is to make door-to-door flying a reality drastically reducing commute times and decongesting our cities for a cleaner greener future. Were a passionate team of engineers designers and visionaries working on cutting-edge technology and were looking for brilliant minds to help us take flight.
Were building the coupled simulation and optimisation capability that informs our aircraft design decisions for now and future. We are looking for a candidate who can build models across domains where you work with our internal ML and software development teams to lead the development of multi-physics simulations and models. You will join our team to transform mathematical models aerospace physics simulations and Reinforcement Learning algorithms into high-throughput low-latency production-grade GPU-accelerated software engines.
Roles and Responsibilities
implement high-performance differentiable numerical solvers from the ground up
Build and validate coupled ML models and systems across complex multi-physics systems
Own verification and validation and tell the Engineering teams on where a model can and cant be trusted
Chain surrogate models built by other teams to enable engineering teams to utilise them
Ensure all physical simulations expose clean analytic gradients (autodiff) so the Optimization team can perform rapid gradient-based design sweeps
Profile and optimize simulation code for maximum throughput on GPU architectures focusing on memory efficiency and execution speed
Build surrogate and reduced-order models from our simulations. These should report their own uncertainty combine cheap and expensive simulations and choose where to sample next
Required Qualifications
Direct experience in physics engine development computational engineering software or high-fidelity simulation environments
Understanding of mathematics particularly linear algebra numerical simulations probability theory differential geometry
Hands-on experience building numerical solvers in NVIDIA Warp JAX or writing custom high-performance CUDA/C compute kernels
Deep knowledge of MDO frameworks and aircraft sizing software.
Familiarity with surrogate modelling using system identification Gaussian processes neural networks
Expertise with Automatic differentiation tools and development
Preferred Qualifications
Deep knowledge of MDO frameworks and aerospace sizing software.
Experience with OpenMDAO or a similar framework for coupling and optimising engineering models.
Experience with multi-objective optimisation using Pareto front methods like NSGA-II MOEA/D SHERPA Adjoint-based optimization
Experience with 3D or other irregular data: meshes point clouds voxels sparse tensors
Understanding of hybrid-electric propulsion integration at the aircraft level
Required Skills:
Required Qualifications Direct experience in physics engine development computational engineering software or high-fidelity simulation environments Understanding of mathematics particularly linear algebra numerical simulations probability theory differential geometry Hands-on experience building numerical solvers in NVIDIA Warp JAX or writing custom high-performance CUDA/C compute kernels Deep knowledge of MDO frameworks and aircraft sizing software. Familiarity with surrogate modelling using system identification Gaussian processes neural networks Expertise with Automatic differentiation tools and development Preferred Qualifications Deep knowledge of MDO frameworks and aerospace sizing software. Experience with OpenMDAO or a similar framework for coupling and optimising engineering models. Experience with multi-objective optimisation using Pareto front methods like NSGA-II MOEA/D SHERPA Adjoint-based optimization Experience with 3D or other irregular data: meshes point clouds voxels sparse tensors Understanding of hybrid-electric propulsion integration at the aircraft level
