Member of Technical Staff — Research

RadixArk is hiring researchers and engineers to train advanced AI models. The role spans the training stack, including data, training recipes, post-training, reinforcement learning, and evaluation, with a focus on improving model performance.

Responsibilities:

• You’ll work on the full training stack, from data and recipes to post-training, RL, and evaluation, alongside a small, high-caliber team building at the frontier of AI systems
• Pre-training, mid-training, and post-training of large models
• Reinforcement learning, reasoning, and reward modeling
• Data, evaluation, and the research behind making models measurably better