Research Post-Training

Thinking Machines Lab is dedicated to advancing collaborative general intelligence and empowering humanity through AI. The role of post-training researchers is essential in bridging raw model intelligence with practical applications, requiring both fundamental research and engineering skills to enhance AI learning processes.

Responsibilities:

• Develop and tune the recipe: iterate on post-training recipes, consisting of a collection of datasets, training stages, and hyperparameters. Measure how recipe choices affect various metrics
• Iterate on evals: post-training involves a never-ending loop of defining a set of evaluations, optimizing them, and then realizing your existing evals don’t capture what matters. You’ll be responsible for both making numbers go up, and making sure the numbers are meaningful
• Debug and understand: while tuning the details of a training configuration, we often observe results that don’t quite make sense. You’ll be responsible for both getting things to work, and developing a deeper understanding, which we can bring to the next problem
• Scale and explore: post-training will involve a combination of scaling the existing methodologies and developing new ones. We’ll want to both measure how performance metrics scale with dataset size, and explore using a completely different kind of training dataset
• Publish and present research that moves the entire community forward. Share code, datasets, and insights that accelerate progress across industry and academia