About the role
A small technology company in Toronto is hiring for this role. You will bring open-source and customer-provided machine learning models up on the company's AI hardware systems, working across the full software stack. The role exists to get models running correctly and quickly, and to make each future bring-up faster.
What you'll do
- Bring up open-source and customer-provided machine learning models on the company's systems
- Work across model translation, graph lowering, compiler optimization, runtime integration and performance tuning
- Diagnose correctness and performance issues across the software stack
- Prototype tools, APIs and automation to speed up future model bring-ups
What you bring
- Hands-on experience with machine learning models, including large language models
- Working knowledge of the software stack, from model translation through compilers and runtime
- Skill at diagnosing correctness and performance problems
- Ability to build internal tools, APIs and automation
Details
- Location: Toronto, Ontario
- Type: Full-time
Apply below and a Traverse recruiter will be in touch.