About this role
Inferact is hiring an Inference Engineering Co-op in San Francisco to work on core AI inference systems alongside the creators of vLLM. This in-office internship suits University of Waterloo co-op students who want to build production-grade, large-scale machine learning infrastructure.
Role Overview
Inferact is seeking exceptional University of Waterloo co-op students to contribute to the systems powering frontier AI models. Interns take on real engineering problems across the vLLM stack, ranging from model execution and low-level accelerator code to distributed serving and cloud platforms. Participants collaborate directly with the creators and core maintainers of vLLM, receiving mentorship from a small, senior team while working on projects intended for open-source and production environments.
Key Responsibilities
Requirements
Nice to Have
Skills and Tools
Salary and Benefits
About the Company
Inferact focuses on growing vLLM as an AI inference engine to make inference cheaper and faster. Founded by the creators and core maintainers of vLLM, the company operates at the intersection of models and hardware.
How to Apply
To apply for this position, please visit the official company careers page.
Skills and tech stack
Questions candidates ask
Who is eligible for this co-op position?
The role is open to students currently pursuing a bachelor's, master's, or PhD degree in computer science, engineering, mathematics, or a related technical field who are eligible for a University of Waterloo co-op work term.
Where is the job located?
The position is in-office only at Inferact's San Francisco, California office.
Will interns work on sandboxed projects?
No, interns work on real engineering problems across the vLLM stack with work intended to ship into open source or production systems.
Are housing benefits provided?
Yes, a housing stipend is provided for the duration of the co-op term alongside competitive compensation.
What programming languages are required?
Candidates need strong programming ability in Python, C++, Rust, Go, or another systems-oriented language.