Senior Applied Research Scientist – GPU Native Numerical Algorithms
€121k - €256k • Remote • Germany, Remote • Full-time
Posted 12h ago
About the job
NVIDIA is seeking an Applied Research Scientist to join its computational engineering applied research team. This role focuses on designing and developing GPU-native numerical methods to enhance the speed, reliability, and usability of engineering simulations across NVIDIA platforms. You will contribute to the numerical foundations for emerging AI-native engineering algorithms by exploring solver algorithms, building research prototypes, and evaluating different approaches. The objective is to rethink traditional CPU algorithms for massive parallelism, hierarchical memory, reduced synchronization, mixed precision, tensor-core computation, and multi-GPU systems, connecting numerical analysis, accelerated computing, software engineering, and AI-native methods.
Responsibilities
- Invent and reformulate numerical algorithms optimized for modern NVIDIA GPU architectures, including implicit and explicit engineering simulation.
- Develop linear and nonlinear solver approaches such as Newton-Krylov methods, multigrid, domain decomposition, matrix-free algorithms, mixed precision, and sparse iterative/direct methods.
- Investigate and reformulate CPU-oriented numerical methods for GPU architectures, focusing on synchronization-avoiding Krylov methods, GPU-native multigrid, matrix-free implicit methods, and sparse direct/iterative hybrids.
- Evaluate algorithms on diverse workloads including mechanics, contact, thermal-fluid systems, electromagnetics, semiconductor simulation, EDA, multiphysics, and related CAE domains.
- Collaborate with internal teams (CUDA-X, Warp, NVIDIA Research) and external partners (universities, industry) to transition research prototypes into NVIDIA software capabilities.
- Contribute to the applied research roadmap for GPU-native numerical methods and their evolution towards AI-native computational engineering.
Requirements
- PhD or equivalent experience in computational mechanics, applied mathematics, scientific computing, computer science, or a related engineering field.
- 5+ years of relevant work or research experience.
- Research or engineering experience in PDE discretization, finite element/volume/discontinuous Galerkin methods, nonlinear solvers, sparse linear algebra, preconditioning, or high-performance computing.
- Proficiency in writing numerical software using C++ and Python.
- Experience developing or optimizing CUDA or GPU code.
- Experience using profiling, benchmarking, numerical validation, or performance analysis to improve algorithms on GPU or multi-GPU systems.
- Ability to clearly communicate technical tradeoffs and collaborate effectively across diverse teams.
Benefits
- Base salary range: 121,275 EUR – 210,210 EUR for Level 4; 147,675 EUR – 255,970 EUR for Level 5.