Senior Software Engineer — cuEquivariance
$184k - $357k • Remote • US, CA, Santa Clara
Posted 1d ago
Job Location
US, CA, Santa Clara
Tech Stack
Remote Work Policy
Fully remote
Categories
Machine Learning Engineer
About the job
NVIDIA BioNeMo is seeking a Senior Software Engineer to join the cuEquivariance team. This team develops and ships production GPU kernels and software interfaces that accelerate geometric neural networks on NVIDIA GPUs, enabling researchers in fields like molecular biology, materials science, and physics to train and deploy equivariant models at scale. The role involves CUDA kernel engineering, Python library development with PyTorch and JAX, and collaboration with research teams and external framework developers. This is an opportunity to work at the intersection of GPU computing and graph-based deep learning, with your work impacting scientific communities through production pipelines.
Responsibilities
- Build, implement, and optimize CUDA kernels for equivariant neural network primitives targeting peak performance across NVIDIA GPU generations.
- Manage the end-to-end delivery of GPU-accelerated geometric ML primitives, ensuring production-quality software for external frameworks.
- Develop and maintain PyTorch and JAX interfaces for cuEquivariance primitives.
- Drive CI/CD infrastructure for multi-GPU kernel builds, automated correctness testing, and performance regression tracking.
- Collaborate with Applied Science and research teams to evaluate new equivariant architectures and translate prototypes into production kernels.
- Engage with third-party framework developers and partners to ensure seamless integration of delivered software into production pipelines.
Requirements
- 6+ years of software engineering experience with a strong background in CUDA and GPU programming.
- Deep proficiency in C++ and Python, with experience building and shipping production libraries for external developers.
- Solid foundation in GPU computing concepts including memory hierarchy, warp-level execution, occupancy, and performance profiling.
- Experience building or contributing to production scientific software libraries, ML frameworks, or developer-facing GPU APIs.
- Sufficient familiarity with geometric machine learning concepts (equivariance, group representations, irreducible representations, tensor products) to work effectively in the domain.
- BS/MS in Computer Science, Physics, Applied Mathematics, or a related field, or equivalent experience.
Benefits
- Highly competitive salaries
- Comprehensive benefits package
- Eligibility for equity
- Eligibility for benefits