# Research Intern, Inference (Summer 2027) at Together AI

> Together AI is hiring for Research Intern, Inference (Summer 2027) in San Francisco, CA (Internship, 0-2 years experience), posted on 1 November 2026.

Canonical: https://devsunite.com/jobs/together-ai-research-intern-inference-summer-2027-san-francisco-nov2026-38d3be
Last updated: 2026-11-01

- **Company**: Together AI
- **Location**: San Francisco, CA
- **Employment type**: Internship
- **Experience**: 0-2 years
- **Role**: Research Intern, Inference (Summer 2027)
- **Salary**: Competitive
- **Posted**: 2026-11-01

## Required skills

- Python
- PyTorch
- JAX
- CUDA
- Machine Learning

## 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&#x27;s, Master&#x27;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.

## How to apply

Sign in on the job page to apply: https://devsunite.com/jobs/together-ai-research-intern-inference-summer-2027-san-francisco-nov2026-38d3be

## Related

- [Together AI internships](https://devsunite.com/companies/together-ai)
- [Tech jobs in USA](https://devsunite.com/jobs-in-usa)
- [All jobs](https://devsunite.com/jobs)
