Developer Technology Engineer - NVIDIA
2 weeks ago⚠️ Before applying, please carefully review all the job requirements
- Location:
- Zurich, Switzerland | UK (Remote) | Germany (Remote) | Saudi Arabia (Remote) | France (Remote) | Dubai UAE (Remote)
- Work Arrangement:
- Remote
- Experience:
- 5+ years of relevant experience in GPU and HPC optimization
- Job Type:
- Full Time
- Company:
- NVIDIA
- Salary:
- Negotiable
- Posted:
- 2026-09-18
- Job Requisition ID:
- JR2018521
Job Overview
- NVIDIA is seeking a highly skilled computer scientist or engineer to join the Compute Developer Technology (DevTech) division as a Developer Technology Engineer focused on the Energy sector. In this role, successful candidates will specialize in accelerating high-performance computing (HPC) and artificial intelligence workflows on NVIDIA hardware platforms. Primary responsibilities involve driving CUDA performance optimizations for computationally intensive energy workloads, such as seismic imaging and inversion pipelines, reservoir simulations, power grid modeling, and related production software. Working directly with external engineering partners and internal product teams, the position focuses on achieving measurable speedups and maximizing scalable performance across multi-GPU and multi-node architectures. This opportunity is well suited for experienced parallel computing professionals interested in advancing computational physics, numerical algorithms, and deep learning integrations within global energy technology ecosystems.
Key Responsibilities
- • Conduct detailed profiling, performance analysis, and optimization of GPU-accelerated codebases with an emphasis on CUDA kernel efficiency, memory throughput, concurrency, and overall execution speed.
- • Enhance application performance across the software stack by optimizing CUDA C++ kernels, stream configurations, memory access patterns, and execution events.
- • Leverage specialized NVIDIA GPU libraries, including cuBLAS, cuFFT, cuSPARSE, cuSOLVER, and NCCL, to accelerate mathematical and linear algebra routines.
- • Implement scalable multi-GPU and multi-node communication schemes using MPI and NCCL while maximizing CPU/GPU execution overlap.
- • Establish benchmark suites, compile technical performance reports, and produce reproducible tuning recommendations featuring before-and-after scaling metrics.
- • Create, maintain, and deliver reference implementations, code examples, and patches for client software to boost speed and cross-platform portability.
- • Partner with customer technical teams during proof-of-concept and production stages to resolve correctness or performance issues and provide deployment best practices for containerized cluster environments.
- • Coordinate with internal engineering teams to report bugs, validate software fixes, and help shape future hardware and software roadmaps based on energy sector demands.
- • Design reusable internal code structures and performance libraries that contribute to future NVIDIA commercial product offerings.
Required Skills and Qualifications
- • Bachelor's or Master's degree (or equivalent practical experience) in Computer Science, Computer Engineering, Electrical Engineering, Physics, Applied Mathematics, or a related discipline.
- • Strong proficiency in C, C++, and Python programming within Linux operating environments.
- • Hands-on development experience using CUDA alongside a deep understanding of GPU architecture performance tuning.
- • Practical familiarity with GPU profiling and debugging tools, such as NVIDIA Nsight Systems, Nsight Compute, or comparable software.
- • Solid grasp of parallel computing principles, including thread management, vectorization, NUMA architectures, memory bandwidth, and latency optimization.
- • Demonstrated ability to articulate technical findings clearly to both technical engineers and non-technical stakeholders.
- • Minimum of 5 years of professional experience in GPU or high-performance computing (HPC) optimization with a documented record of delivering software speedups and scaling enhancements.
Preferred Qualifications
- • Track record of leading technical performance evaluations with customer stakeholders and designing reusable implementation playbooks.
- • Advanced background in high-performance computing involving MPI, distributed network architectures, and multi-node cluster tuning.
- • Domain experience in energy computing workflows, such as seismic imaging (RTM/FWI, stencil, FFT, linear algebra), reservoir simulations (sparse iterative solvers, preconditioning, domain decomposition), or power grid stability and optimization modeling.
- • Experience configuring continuous integration, performance regression testing, container platforms (Docker or Apptainer), and workload schedulers like Slurm.
- • Knowledge of integrating artificial intelligence models (data preparation, training, and inference execution) alongside conventional simulation pipelines.
Application Tips
- Applicants may want to highlight relevant experience with GPU software acceleration, CUDA kernel development, and high-performance computing projects in their technical CV. Emphasizing specific measurable achievements—such as benchmark performance gains, scaling metrics on multi-GPU systems, or execution speedups achieved in previous roles—can effectively demonstrate technical impact. Candidates should consider detailing their familiarity with Linux environments, profiling toolkits like NVIDIA Nsight, and C++ or Python code repositories. Demonstrating domain exposure to scientific computing, linear algebra libraries, or energy sector simulation frameworks will also provide valuable context regarding suitability for this position.
Ideal Candidates Fill the Job Form: Apply Here
