Senior Compiler Engineer

Key Skills

Aartificial intelligence, Business Development, C++, Data science techniques, Python Programming, PyTorch, TensorFlow

Job Description

Please note: While our engineering HQ is in Toronto, this is a remote opportunity and we welcome applicants from anywhere in North America.

We are looking for compiler experts to help unlock the potential of Untether AI’s spatial compute architecture. In this role, you will be expected to develop solutions to the unique problems presented by a spatial architecture. Your playground would include a high-level graph compiler, a low-level conventional compiler and everything in between. The problems are simultaneously similar enough to those of conventional compilers that you will know where to start while having spatial twists that make them new and fresh. Comfort tackling new domains is a definite asset!

Requirements

• Computer Science, Engineering, or related degree
• 5+ years of experience
• Experience developing the internals of modern optimizing compilers
• Creative problem solver, passionate about solving hard problems
• Expertise in combinatorial and graph optimization algorithms
• Strong C++ and python development skills
• Experience delivering high-performance software to production

Preferred Skills & Experience

• Masters or PhD in Computer Science, Engineering, or related field
• Relentless focus on software quality and testing
• Experience tuning and optimizing code for high performance
• Proficient with python data-science libraries (pandas, numpy, bokeh)
• Familiar with neural net frameworks tensorflow or pytorch
• Experience working with continuous integration systems

Don't meet all the requirements but still feel like you'd be a good fit for the role? We encourage you to apply regardless.

About Untether AI:

Untether AI is 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, Untether AI’s 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.