AI Researcher

Sourced from jobs.accel.com

RadixArk is seeking researchers and engineers to work across the full large-model training stack, from data and recipes to post-training, reinforcement learning, and evaluation. The role sits within a small, high-caliber team building at the frontier of AI systems.

• Work on pre-training, mid-training, and post-training of large models
• Develop reinforcement learning, reasoning, and reward modeling approaches
• Drive data, evaluation, and research to make models measurably better

• Track record of research or engineering on large-model training
• Focus on shipping results rather than only publishing
• Curious, direct, and comfortable with ambiguity