Research, Mid Training

Job summary

Responsibilities

Mid-training is a step between pre-training and post-training, where we take a base model and train it into the foundation for reasoning. This role owns the late-stage training responsibility that shape what our models are fundamentally capable of, including things like synthetic data strategies…

• Own the data. Decide what the model needs to see for each capability and each area of knowledge, then source, curate, and synthesize it.
• Improve what the model knows. Design and measure interventions that increase knowledge: targeted corpora, synthetic rephrasings and QA over source documents, knowledge-dense…
• Instill behaviors and set the prior. Introduce new behaviors during mid-training and measure them the right way: not just whether an eval goes up, but whether post-training…
• Build the quality pipeline. Own the automatic filtering and scoring stack: train and calibrate quality classifiers and LLM-based judges, build verifiers for synthetic data, and…
• Develop and tune the recipe. Iterate on mid-training recipes: the collection of datasets, training stages, annealing schedules, and hyperparameters.

What they're looking for

• Proficiency in Python and familiarity with deep learning frameworks (e.g., PyTorch, TensorFlow, or JAX). Comfort debugging distributed training and writing code that scales.
• Bachelor’s degree or equivalent experience in Computer Science, Machine Learning, Physics, Mathematics, or a related discipline with strong theoretical and empirical grounding.
• Clarity in communication, an ability to explain complex technical concepts in writing.
• A strong grasp of probability, statistics, and ML fundamentals. You can look at experimental data and distinguish between real effects, noise, and bugs.
• Experience building or owning training datasets for large models, including both synthetic data pipelines and real user data (collection, curation, filtering, or mixture design).

Tech stack

• Python
• PyTorch
• TensorFlow
• JAX