Research Intern Inference Summer 2027
Together AIVisit Together AI website
Together AI operates an AI-native cloud platform for open and custom AI models.
San Francisco, United States
About Together AI
Together AI provides production AI infrastructure spanning inference, accelerated compute, model training and fine-tuning, and secure code sandboxes for AI development.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will research distributed inference, compiler-aware optimization, and inference-time computation. You will design and conduct rigorous experiments, communicate project progress and results, and document findings in publications and blog posts. You will explore cross-layer optimization across models, systems, hardware, caches, and serving architectures.
Requirements
- Machine learning
- Deep learning
- PyTorch
- JAX
- Python
- Transformer
- Foundation model
Responsibilities
- Design and conduct rigorous experiments
- Communicate project plans, progress, and results
- Document findings in scientific publications and blog posts
Benefits
- Housing stipend