Research Intern - LLM Performance Optimization

This role is based in Redmond, Washington.

Compensation:

USD $6,710 - $13,270 per month

Responsibilities:

Research Interns will collaborate with doctoral candidates and researchers, contribute to research and development, present findings, and engage in a vibrant community over a 12-week internship.

Qualifications:

• Currently enrolled in a PhD program in Computer Science or a related STEM field.
• At least 1 year of experience with Large Language Model architecture or inference performance optimization.

Preferred Qualifications:

• Ability to assess and fix kernel performance bottlenecks for GPUs or high-performance parallel architectures.
• Familiarity with optimizing compiler architecture.
• Creative problem-solving skills.