GPU Systems Research Intern: High-Performance AI

Together; San Francisco (CA); On-site; USD 80,000 - 96,000; Full time

Benefits offered by this job

Housing stipend

Competitive benefits

Job summary

Together AI in San Francisco is seeking a Systems Research Engineer Intern focused on GPU programming to develop and optimize GPU-accelerated kernels for ML/AI applications. You will co-design kernels with the modeling team and work with hardware/software groups to improve AI system performance.

The internship runs on-site from January to April at the SF HQ, offering exposure to cutting-edge GPU research and collaborative engineer environments.

Qualifications

• Strong background in GPU programming and parallel computing.
• Familiarity with CUDA and/or Triton architectures and APIs.
• Knowledge of ML/AI applications and models.
• Experience with performance profiling and GPU optimization tools.

Responsibilities

• Optimize and fine-tune GPU kernels for ML/AI workloads.
• Collaborate with cross-functional teams to integrate GPU-accelerated solutions.
• Stay current with new GPU programming techniques and hardware trends.

Skills

GPU programming

Parallel computing

CUDA / Triton

ML/AI familiarity

Job description

Together AI in San Francisco is seeking a Systems Research Engineer Intern focused on GPU programming to develop and optimize GPU-accelerated kernels for ML/AI applications. You will co-design kernels with the modeling team and work with hardware/software groups to improve AI system performance.

The internship runs on-site from January to April at the SF HQ, offering exposure to cutting-edge GPU research and collaborative engineer environments.