Artificial Intelligence

Research Intern, Inference (Winter 2027)

San Francisco, CAOnsiteInternshipJunior / Entry-level$58,000–$70,000 /yrPosted 1 month ago

Is this role right for you?

Upload your resume and get a skill-by-skill breakdown — see exactly where you match, where you're close, and what to highlight. Not a mystery percentage.

Get a tailored resume highlighting what this role needs.

Required skills

Foundation Models
Inference
Distributed Inference
Compiler-aware Optimization
Speculative Decoding
Phase-aware Execution
KV Cache Design
Large-scale Serving Architectures
Mixture-of-Experts
Serving Workloads

Nice to have

Research Experience
Efficient Machine Learning
ML Systems
MLSsys
ICLR
CUDA Programming

Role summary

Together AI is seeking Research Interns for its Inference Research team for Winter 2027. This role focuses on building efficient, scalable, and reliable serving systems for large foundation models, contributing to open and transparent AI. Interns will work on distributed inference, compiler optimization, and novel inference-time computation strategies. Responsibilities include designing and conducting experiments, communicating findings, and documenting results. The ideal candidate is pursuing a final year Bachelor's, Master's, or Ph.D. in a related field, with strong Machine Learning/Deep Learning fundamentals, experience with deep learning frameworks (PyTorch, JAX), Python programming skills, and familiarity with Transformer architectures. Preferred qualifications include prior research experience, publications, CUDA programming, and model optimization knowledge.

About The Role

The Inference Research team is dedicated to building the next generation of efficient, scalable, and reliable serving systems for large foundation models, directly contributing to the mission of advancing open and transparent AI. Our work operates at the critical intersection of cutting-edge model architectures, high-performance systems engineering, and deep hardware optimization. We focus on co-designing software, algorithms, and models to significantly lower the cost and latency of modern AI systems.

As a research intern, you will dive into the complexities of distributed inference, compiler-aware optimization, and novel inference-time computation strategies (such as speculative decoding and phase-aware execution). You will be tasked with co-designing and implementing cross-layer optimizations across models, systems, and hardware, with a focus on areas like KV cache design and large-scale serving architectures.

Projects aim to unlock unprecedented performance and scale for foundation models, enabling faster serving, larger model deployment (e.g., Mixture-of-Experts), and robust, reproducible evaluation under realistic serving workloads.

Responsibilities

Design and conduct rigorous experiments to validate hypotheses

Communicate the plans, progress, and results of projects to the broader team

Document findings in scientific publications and blog posts

Requirements

Currently pursuing a final year of Bachelor's, Master's, or Ph.D. degree in Computer Science, Electrical Engineering, or a related field

Strong knowledge of Machine Learning and Deep Learning fundamentals

Experience with deep learning frameworks (PyTorch, JAX, etc.)

Strong programming skills in Python

Familiarity with Transformer architectures and recent developments in foundation models

Preferred Qualifications

Prior research experience in foundation models, efficient machine learning, or ML systems.

Publications at leading conferences in machine learning or systems (i.e., 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

About Together AI

Together AI, the AI Native Cloud, is purpose-built for AI engineers. AI application developers get high-performance inference that scales reliably, fine-tuning and reinforcement learning for creating frontier-level specialized models, and pre-training at massive scale for fully custom intelligence, all around a marketplace of leading open models that teams can run, adapt, and own. Trusted by Cursor, Decagon, ElevenLabs, Salesforce, and Zoom, Together serves 400+ trillion tokens a month.

Internship Program Details

Our internship program runs 12 to 14 weeks, giving you the opportunity to work alongside industry-leading engineers and researchers across multiple teams. This cohort's internship dates span January 4th to April 9th.

Compensation

We offer competitive compensation, housing stipends, and other competitive benefits. The estimated US hourly rate for this role is $58 to $70 an hour. Our hourly rates are determined by location, level and role. Individual compensation will be determined by experience, skills, and job-related knowledge.

Application Policy

Please read each role carefully and apply to the position best suited to you. Candidates are limited to 6 applications within a 90-day period, and applications beyond that limit will be automatically rejected. You may apply to additional roles 90 days after your last application.

Equal Opportunity

Together AI is an Equal Opportunity Employer and is proud to offer equal employment opportunity to everyone regardless of race, color, ancestry, religion, sex, national origin, sexual orientation, age, citizenship, marital status, disability, gender identity, veteran status, and more.

Please see our privacy policy at https://www.together.ai/privacy

Ready to apply?

You'll be redirected to Together AI's application page.