Together AI logo for Research Intern, Inference (Summer 2027) job on DevsUnite

Research Intern, Inference (Summer 2027)

Together AI

Actively HiringInternship
Apply
Location

San Francisco, CA

Experience

0-2 years

Role

Research Intern, Inference (Summer 2027)

Salary

Competitive

Share this job

Know someone who'd be a great fit?

Job Description

Role Overview

The Inference Research team builds efficient, scalable serving systems for large foundation models. As a research intern, you will explore distributed inference, compiler‑aware optimization, and inference‑time techniques such as speculative decoding and phase‑aware execution, focusing on KV cache design and large‑scale serving architectures. You will use Python, PyTorch, and JAX to prototype and evaluate solutions.

Responsibilities

  • Design and conduct rigorous experiments to validate hypotheses.
  • Implement cross‑layer optimizations across models, systems, and hardware.
  • Communicate plans, progress, and results to the broader team.
  • Document findings in scientific publications and blog posts.

Requirements

  • Pursuing a final year of Bachelor's, Master's, or Ph.D. in Computer Science, Electrical Engineering, or a related field.
  • Strong knowledge of Machine Learning and Deep Learning fundamentals.
  • Experience with deep learning frameworks such as PyTorch or JAX.
  • Proficient in Python programming.
  • Familiarity with Transformer architectures and recent foundation model developments.

Preferred Qualifications

  • Prior research experience in foundation models, efficient Machine Learning systems.
  • Publications at leading conferences in Machine Learning or systems (e.g., MLSys, ICLR).
  • Experience with CUDA programming for kernel development.
  • Understanding of model optimization techniques and hardware acceleration approaches.
  • Contributions to open‑source Machine Learning projects.

Compensation

The role offers competitive compensation, housing stipends, and other benefits. The estimated US hourly rate is $58 to $70, determined by location, level, and role.

Internship Details

The internship runs 12 to 14 weeks, with start dates in May or June 2027, and provides an opportunity to work alongside industry‑leading engineers and researchers.

Benefits

Competitive compensation, housing stipends, and a comprehensive benefits package.

Required Skills

PythonPyTorchJAXCUDAMachine Learning

Ready to apply for Research Intern, Inference (Summer 2027)?

See how you stack up at Together AI before you apply, or go straight to the application.

Apply Anyway