Research Intern Frontier Speculative Decoding
Together AIVisit Together AI website
Together AI operates an AI-native cloud platform for open and custom AI models.
Series CRecently funded
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 speculative decoding algorithms and draft-model architectures, train and fine-tune models, and run rigorous experiments. You will implement optimized serving-engine versions, communicate project results, publish technical findings, and help bring successful research ideas into production.
Requirements
- Master's or Ph.D. degree in Computer Science, Electrical Engineering, or a related field in progress
- Knowledge of machine learning and deep learning fundamentals
- Experience training or fine-tuning large models with distributed training frameworks
- Familiarity with Mixture-of-Experts and hybrid attention model architectures
Responsibilities
- Research and prototype speculative decoding algorithms and draft model architectures
- Train, fine-tune, and distill draft models
- Design experiments to validate hypotheses
- Implement optimized versions for serving engines
- Communicate project plans, progress, and results
- Share findings through technical write-ups and blog posts
- Help bring successful ideas into production
Benefits
- Housing stipends