Senior Software Engineer, Scientific Evaluation

NVIDIA Gruppe; Santa Clara (CA); On-site; USD 152,000 - 288,000; Full time

Job summary

NVIDIA seeks a Software Engineer - Scientific Evaluation to own a shared platform for testing, benchmarking, and agentic evaluation across CUDA, C++, and Python ecosystems.

You will design infrastructure and indicators to deliver reproducible results, manage GPU resources with schedulers, and collaborate with scientists and engineers to ensure production readiness and scalable quality signals.

Qualifications

• A BS or MS in Computer Science, Computer Engineering, or a related field.
• 5+ years of relevant industry experience.
• Strong CS fundamentals and production C++/Python skills.
• Experience with Linux, Git workflows, CI/CD pipelines, CMake, Docker.
• Experience building test/benchmark/evaluation/distributed systems with reproducible results.
• Experience with Slurm, Kubernetes or similar schedulers and monitoring.

Responsibilities

• Own the architecture and roadmap for evaluation and benchmarking of scientific software, serving agentic and numerical evaluations.
• Design and implement infrastructure, benchmarks and test levels for classical software and scientific agents, balancing rapid turnaround time and thorough scientific coverage.
• Establish trusted references, numerical tolerances, calibrated scorers, regression thresholds, and human-review hooks for nondeterministic workloads.
• Operate heterogeneous GPU capacity using multiple control plane technologies, self-hosted runners, schedulers, queues, containers, caching, observability, and automated recovery.
• Collaborate with applied scientists, kernel/framework engineers, product teams, and release owners to produce reproducible quality signals and production-readiness gates.

Skills

C++ production

Python

Linux

Git/GitHub CI

Docker/Kubernetes

Distributed systems

Education

BS/MS in Computer Science

Tools

Slurm

Kubernetes

CMake

Docker

Job description

NVIDIA seeks a Software Engineer - Scientific Evaluation to own a shared platform for testing, benchmarking, and agentic evaluation across CUDA, C++, and Python ecosystems.

You will design infrastructure and indicators to deliver reproducible results, manage GPU resources with schedulers, and collaborate with scientists and engineers to ensure production readiness and scalable quality signals.