Principal AI Research Scientist

Focusing on post-training alignment and reinforcement learning, the full-time Principal AI Research Scientist will develop novel algorithms, design experiments, and contribute to publications while working remotely or from various locations in the US, Canada, or Europe. Key responsibilities Lead post-training model development, including RLHF and long-horizon reasoning Design and execute experiments to enhance model behavior and robustness Collaborate with infrastructure teams to create scalable post-training workflows Required qualifications Deep expertise in reinforcement learning and post-training methods Proven experience leading technical research teams in academic or industry settings Strong intuition for model behavior and alignment challenges PhD or equivalent research experience in ML, RL, AI, or a related field Strong publication record in leading ML or AI venues