Responsibilities
- Design and implement components of a machine learning graph compiler
- Collaborate on the joint development of hardware and software platforms
- Evaluate, measure, and enhance the performance of critical machine learning workloads across the full stack
- Build tools and systems for performance modeling and prediction that support compiler optimization
- Create a high-efficiency runtime engine for AI workloads
- Enable integration of the software platform with major machine learning frameworks
- Partner with machine learning teams to understand current and emerging application needs
- Design and implement new machine learning models and operations that leverage architectural innovations for significant performance gains
Compensation
Compensation for all interns ranges from $50/hr to $70/hr, inclusive of base and variable components
Work Arrangement
On-site — Austin, TX, Santa Clara, CA, Toronto, ON
Team
Team works at the intersection of compiler design, machine learning, and hardware architecture to deliver optimized AI computing solutions
Other
- Intern compensation ranges from $50 to $70 per hour, including base and variable targets
- Final offers depend on experience, skills, education, background, and location
- A competitive compensation and benefits package is offered
- Employment is subject to eligibility to access U.S. export-controlled technology
- Compliance with U.S. Export Administration Regulations (EAR) is required, including restrictions related to certain countries (e.g., EAR Country Groups D:1, E1, E2)
- These regulations apply globally, regardless of applicant location
- The role may require verification of citizenship, permanent residency, or prior approval from the U.S. Commerce Department due to access to controlled technology
- Any offer of employment may be withdrawn if compliance with U.S. export laws cannot be achieved
Not applicable
