logo

View all jobs

Compiler Design Engineer

Remote, Toronto · Computer/Software
We are looking for an experienced Compiler Engineer. The ideal candidate will have extensive experience building compilers for a variety of architectures, working with established frameworks such as LLVM, and intimate understanding of the full compilation life-cycle. 

The compiler team is responsible for creating software that translates a wide variety of neural nets into efficient mappings and fast implementations on our accelerator hardware, from data-in to data-out. In this role, you will design and architect key components of the compilers, mentor junior team members, and take part in designing our next generation of hardware.

Responsibilities

    • Design and implement software that maps a neural net onto our unique spatial architecture
    • Stay abreast of latest developments in network compilation and optimization, and bring those learnings to our tool flow
    • Drive definition and adoption of best practices
    • Support roadmap development, planning, and recruiting activities, and help maintain a productive environment in the team
    • Work closely with upstream and downstream teams
    • Mentor and guide junior engineers
    • Evaluate current and proposed hardware architecture for future products

Preferred Skills & Experience

    • Computer Science, Engineering or related degree; Preferably MS or PhD
    • 5+ years experience developing the internals of modern optimizing compilers for a variety of architectures
    • Understanding of advanced optimization techniques
    • Thorough understanding of deep neural nets a bonus
    • Experience with LLVM a must, experience with MLIR a bonus
    • Experience with spatial computing architectures or massively parallel systems
    • Experience with benchmarking and performance guided optimization
    • Driven and self-directed
    • Proficiency in a variety of development styles and languages
    • Ability to build projects from the ground up
    • Comfortable working within a rapidly evolving project
    • Strong focus on testing and software quality
    • Team focus and desire to help build the team

About The Company:

We are developing a groundbreaking new architecture that will bring neural net inference to new levels of performance and efficiency. Founded in Toronto in 2018 by a team of scientists and entrepreneurs, our ultra-efficient, high performance AI chips will eliminate the data movement bottleneck that costs energy and performance in traditional architectures. With the support of tier one investors, we are challenging the status quo with an architecture that is fundamentally unique. Working with us means getting the opportunity to be a part of something big - a chance to create the future of AI.

Share This Job

Powered by