AI Researcher

RadixArk; San Francisco (CA); On-site; USD 180,000 - 280,000; Full time

Job summary

RadixArk is seeking researchers and engineers who enjoy training the best AI models. You’ll work on the full training stack—from data and recipes to post-training, RL, and evaluation—alongside a small, high-caliber team pushing the frontier of AI systems.

You may work on pre-training, mid-training, and post-training of large models, reinforcement learning, reasoning, and reward modeling, with a strong emphasis on shipping results and measurable improvements.

Qualifications

• Experience with training large AI models across full stack (data, recipes, post-training)
• Track record of research or engineering on large-model training
• Interest in shipping results, not only publishing

Responsibilities

• Work on pre-training, mid-training, and post-training stages of large models
• Contribute to reinforcement learning, reasoning, and reward modeling
• Handle data workflows and evaluation to improve model performance

Skills

Large-model training

Reinforcement learning

Model evaluation

Job description

About the role

We're looking for researchers and engineers who love training the best AI models. 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.

What you might work on

• 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

You might be a fit if you

• Have a track record of research or engineering on large-model training

• Care about shipping results, not just publishing them

• Are curious, direct, and comfortable with ambiguity