2 days ago
Toronto, CanadaSenior
Responsibilities
- Build, develop, and maintain high-performance runtime and compiler components for end-to-end inference optimization.
- Define mappings of large-scale inference workloads onto NVIDIA systems.
- Extend and integrate NVIDIA’s software ecosystem, including libraries, tooling, and interfaces for model deployment.
- Benchmark, profile, and monitor compiler and inference performance and efficiency metrics.
- Collaborate with hardware architects and design teams on software observations, future architectures, and codesigned features.
- Prototype and evaluate graph transformations, scheduling strategies, and memory/layout optimizations for spatial processors.
- Publish and present technical work on compilation approaches for inference and spatial accelerators.
Requirements
- MS or PhD in Computer Science, Electrical/Computer Engineering, or a related field, or equivalent experience, with five years of relevant experience.
- Strong systems-level software engineering skills using C, C++, and/or Rust, with fundamentals in data structures, algorithms, and concurrency.
- Hands-on compiler or runtime development experience, including IR design, optimization passes, or code generation.
- Experience with LLVM and/or MLIR, including custom passes, dialects, or integrations.
- Familiarity with TensorFlow, PyTorch, and portable graph formats such as ONNX.
- Understanding of parallel and heterogeneous architectures including GPUs, spatial accelerators, or domain-specific processors.
- Experience using profiling, tracing, and benchmarking tools to improve performance, plus strong analytical, debugging, communication, and collaboration skills.
- Preferred qualifications include MLIR-based compiler experience, spatial or dataflow architecture work, open-source contributions, distributed inference or training experience, performance modeling, capacity planning, and relevant research publications or presentations.
Benefits
- Hybrid work arrangement indicated by #LI-Hybrid.
- Eligible for equity and benefits.
- Applications accepted at least until November 3, 2026.
Categories
About Nvidia
Nvidia designs and sells GPUs and accelerated computing platforms for data centers, AI/ML, graphics, gaming, and automotive, monetizing through hardware, software platforms (CUDA, AI frameworks), and systems like DGX and networking. Customers include cloud providers, enterprises, researchers, and OEMs. Founded in 1993 and headquartered in Santa Clara, it is a public company traded on NASDAQ under NVDA.