Inference Engineering, Co-op

About Inferact

Inferact grows vLLM as an AI inference engine, making inference faster and cheaper.

What you'd do

• Work on model execution and accelerator code
• Contribute to distributed serving and cloud platform
• Implement new inference techniques and architectures
• Build the operational platform for large-scale inference

What they're looking for

• Pursuing a degree in computer science, engineering, or math
• Strong programming skills in Python, C++, Rust, or Go
• Ability to learn from complex systems code
• Experience building nontrivial software through various work

Perks

• Competitive compensation with a housing stipend