Senior Machine Learning Applications and Compiler Engineer, LPX

Description

The company is hiring a senior engineer to build algorithms and optimizations for its inference and compiler stack, working where large-scale systems, compilers and deep learning meet.

Your work will shape how neural network workloads are mapped onto upcoming platforms.

This is an existing open role.

Responsibilities

• Build and maintain fast runtime and compiler components with a focus on optimizing inference from end to end.
• Define and implement how large inference workloads run on the company's systems.
• Contribute to libraries, tooling and interfaces that let models deploy smoothly across platforms.
• Benchmark and profile performance and efficiency, confirming the compiler produces efficient mappings of neural network graphs onto inference hardware.
• Work with hardware architects and design teams to pass along software findings, influence future architectures and co-design features that raise performance and efficiency.
• Prototype and test new compilation and runtime methods, such as graph transformations, scheduling strategies and memory and layout optimizations for spatial processors.
• Publish and present your work on compilation for inference and spatial accelerators at leading ML, compiler and computer architecture venues.

Requirements

• An MS or PhD in computer science, electrical or computer engineering, or a related field, or equivalent experience, plus 5 years of relevant experience.
• Strong software engineering skills in systems programming, such as C/C++ and/or Rust, with solid knowledge of data structures, algorithms and concurrency.
• Hands-on experience building compilers or runtimes, including IR design, optimization passes or code generation.
• Experience with LLVM and/or MLIR, such as writing custom passes, dialects or integrations.
• Familiarity with deep learning frameworks such as TensorFlow and PyTorch, and experience with portable graph formats such as ONNX.
• A solid grasp of parallel and heterogeneous architectures, including GPUs, spatial accelerators and other domain-specific processors.
• Strong analytical and debugging skills, with experience using profiling, tracing and benchmarking tools to improve performance.
• Clear communication and the ability to collaborate across hardware, systems and software teams.
• Ideal candidates have direct experience with MLIR-based compilers or other multilevel IR stacks, especially for graph-based deep learning workloads.
• Ways to stand out: experience with spatial or dataflow architectures, including static scheduling, pipeline parallelism or tensor parallelism at scale.
• Ways to stand out: contributions to open-source ML frameworks, compilers or runtime systems, especially around performance or scalability.
• Ways to stand out: published or presented research at venues such as PLDI, CGO, ASPLOS, ISCA, MICRO, MLSys, NeurIPS or similar.
• Ways to stand out: experience with large-scale distributed AI inference or training systems, including performance modeling and capacity planning for multi-rack deployments.

Conditions

Hybrid work arrangement.

Base salary depends on location, experience and other objective job-related factors: 135,000 CAD to 185,000 CAD for Level 3, and 170,000 CAD to 220,000 CAD for Level 4.

Applications are accepted until at least November 3, 2026.

The company uses AI tools in its recruiting process.