Machine Learning Applications and Compiler Engineer, New College Grad

This is a fully remote position, open to applicants in Canada.

📋 Description

• Design, develop, and sustain high-performance runtime and compiler components, focusing on optimizing end-to-end inference.

• Establish and implement mappings for large-scale inference tasks onto NVIDIA’s systems.

• Enhance and integrate within NVIDIA’s software ecosystem, contributing to libraries, tools, and interfaces that facilitate seamless model deployment across various platforms.

• Benchmark, profile, and monitor essential performance and efficiency metrics to ensure the compiler produces effective mappings of neural network graphs to our inference hardware.

• Work closely with hardware architects and design teams to provide software insights, influence future architectures, and co-design features that unlock new performance and efficiency levels.

• Prototype and assess novel compilation and runtime techniques, including graph transformations, scheduling methods, and memory/layout optimizations tailored for spatial processors.

• Publish and present technical findings on innovative compilation techniques for inference and related spatial accelerators at leading ML, compiler, and computer architecture conferences.

⛳️ Requirements

• Currently pursuing or recently earned a MS or PhD in Computer Science, Electrical/Computer Engineering, or a related field, or possess equivalent experience.

• Strong background in software engineering, with familiarity in systems-level programming (e.g., C/C++ and/or Rust) and solid computer science fundamentals in data structures, algorithms, and concurrency.

• Practical experience in compiler or runtime development, including IR design, optimization passes, or code generation.

• Experience working with LLVM and/or MLIR, including the creation of custom passes, dialects, or integrations.

• Knowledge of deep learning frameworks such as TensorFlow and PyTorch, along with experience utilizing portable graph formats like ONNX.

• Understanding of parallel and heterogeneous computing architectures, such as GPUs, spatial accelerators, or other domain-specific processors.

• Strong analytical and debugging skills, with experience leveraging profiling, tracing, and benchmarking tools to enhance performance.

• Excellent communication and collaboration abilities, with a proven capacity to work across hardware, systems, and software teams.

🏝️ Benefits

• Eligible for equity

• Health insurance

• Stock options

• Paid time off

• Professional development opportunities