Research Engineer, Frontier Speculative Decoding

About the Role

Together AI is building the Inference Platform that powers the world's most advanced generative AI models. Your role will be a critical bridge between cutting-edge research and real-world applications, focusing on making translating our internal model training research to production-ready deployment for our customers. This involves a deep commitment to data-centric development, meticulous hyperparameter tuning, and rigorous checkpoint evaluation before models ever hit production.

This role will involve understanding customer specific needs and fine-tuning models on our internal data recipe and their proprietary data. The goal is to transform general-purpose models into highly performant, specialized tools that solve real business problems. You will not be training foundation models from scratch but rather focusing on creating highly efficient, specialized models by working with dedicated GPU clusters.

Responsibilities

• Design and iterate on novel speculator algorithms, combining architectural innovations with carefully curated data to push the frontier of accuracy–efficiency tradeoffs.
• Be the critical link between raw data and a production-ready model, seeing your work directly impact our customers' success.
• Work in a fast-paced, high-impact role at the cutting edge of generative AI.
• Collaborate with a team of experts dedicated to solving real-world, high-performance challenges.
• You'll collaborate directly with customers to understand their needs, and work closely with our core inference and Applied ML research teams to integrate your work into the production platform.
• A culture of deep technical ownership where you are empowered to take on and solve challenging problems.

Requirements

• A genuine love for data curation and processing, with a meticulous attention to detail. You believe that great models start with great data.
• Demonstrated ability to perform effective hyperparameter searches and understand the trade-offs involved in tuning models for specific tasks.
• Experience working with and building on top of existing training codebases. You are comfortable navigating complex code and contributing to its improvement.
• Strong attention-to-detail in evaluating model checkpoints to ensure they meet strict quality, performance, and reliability standards.
• Experience with Python and PyTorch.
• Familiarity with SLURM and/or Kubernetes clusters and experience submitting and managing jobs in a high-performance computing environment.
• Familiarity with modern LLMs and generative models.
• Basic understanding of distributed training frameworks (e.g., FSDP, DeepSpeed).
• Bachelor’s, Master’s degree, or Ph.D. in Computer Science, Computer Engineering, or a related field, or equivalent practical experience.