Inference Research Intern: Build Scalable AI Serving

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

Benefits offered by this job

Housing stipend

Competitive compensation

Job summary

Together AI in San Francisco is seeking a research intern to accelerate inference systems for large foundation models. You will explore distributed inference, compiler-aware optimization, and cross-layer strategies across models, systems, and hardware.

Join a collaborative team, publish findings, and contribute to faster serving and scalable deployment, with a 12–14 week program from January through April, housing stipends, and competitive hourly compensation.

Qualifications

• Final year student in CS/EE or related field
• Strong ML/DL fundamentals
• Experience with PyTorch or JAX
• Strong Python programming
• Familiarity with Transformer architectures and foundation models

Responsibilities

• Design and conduct rigorous experiments
• Communicate plans, progress, and results
• Document findings in publications and blogs

Skills

ML fundamentals

Deep Learning

PyTorch/JAX

Python

Transformer models

Education

Pursuing final year of Bachelor's, Master's, or Ph.D.

Tools

CUDA

Job description

Together AI in San Francisco is seeking a research intern to accelerate inference systems for large foundation models. You will explore distributed inference, compiler-aware optimization, and cross-layer strategies across models, systems, and hardware.

Join a collaborative team, publish findings, and contribute to faster serving and scalable deployment, with a 12–14 week program from January through April, housing stipends, and competitive hourly compensation.