Skip to main content
Share:
Together AIyesterday

Research Intern, Inference

🇺🇸USSan Francisco, United Statesintern$58 - $70 / hour

Recruiter Fit Breakdown & Candid Summary

1

This 12-to-14-week research internship targets students in their final year of a Bachelor's, Master's, or Ph.D. program in Computer Science or related fields.

2

The role involves deep systems engineering, hardware optimization, and co-designing software for foundation model inference.

3

Ideal candidates have strong PyTorch/Python skills, deep learning fundamentals, and ideally prior research experience or publications in MLSys or ICLR.

4

Candidates lacking foundational knowledge in machine learning, Transformers, or programming in Python should not apply.

Role Responsibilities

  • 1Design and conduct rigorous experiments to validate hypotheses in distributed inference and serving systems
  • 2Communicate plans, progress, and results of projects to the broader team
  • 3Document findings in scientific publications and blog posts
  • 4Co-design and implement cross-layer optimizations across models, systems, and hardware
  • 5Focus on areas such as KV cache design, speculative decoding, and large-scale serving architectures

Skills Matrix

Must-Have Skills

5 required
Machine Learning(ML)
Deep Learning(DL)
PyTorch
Python
Transformer architectures(Transformers)

Nice-to-Have Skills

3 preferred
JAX
CUDA programming(CUDA)
Machine Learning Systems(MLSys)
Free Instant Match Check

Will an ATS filter reject your resume for this role?

Check your keyword match score, missing must-have skills, and formatting flags — before you apply.

Checking saved resume…

No signups. Free check in 3 seconds.

Ready to submit your application?

Apply directly on Together AI's official job portal.