Inference Research Intern — Efficient ML Systems

Togetherai; 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, the AI Native Cloud, invites ambitious students to join the Inference Research team for an internship focused on distributed inference, compiler-aware optimization, and novel inference-time strategies. You will co-design cross-layer optimizations across models, systems, and hardware.

Preferred candidates are in final-year BS/MS/PhD programs, with strong ML/DL fundamentals, Python skills, and familiarity with PyTorch or JAX. Housing stipends and competitive benefits are provided.

Qualifications

• Currently pursuing final year in CS/EE or related field.
• Strong ML and DL fundamentals with Python proficiency.
• Experience with PyTorch or JAX and Transformer concepts is preferred.

Responsibilities

• Design and conduct rigorous experiments to validate hypotheses.
• Communicate plans, progress, and results to the team.
• Document findings in publications or blogs.

Skills

Machine Learning basics

Deep Learning fundamentals

Python programming

Transformer architectures

Education

Final year Bachelor's/Master's/Ph.D. in CS/EE

Tools

PyTorch

JAX

CUDA

Job description

Together AI, the AI Native Cloud, invites ambitious students to join the Inference Research team for an internship focused on distributed inference, compiler-aware optimization, and novel inference-time strategies. You will co-design cross-layer optimizations across models, systems, and hardware.

Preferred candidates are in final-year BS/MS/PhD programs, with strong ML/DL fundamentals, Python skills, and familiarity with PyTorch or JAX. Housing stipends and competitive benefits are provided.