Post-training for model development
Develop novel algorithms that improve model reliability, controllability, and alignment
Design and run experiments that shape model behavior
Partner with infrastructure teams to build scalable, reproducible workflows
Contribute to publications, patents, and external research visibility
Drive human-in-the-loop evaluation with high annotation quality
Communicate technical risks, limitations, and trade-offs clearly to leadership

Deep hands-on expertise in reinforcement learning for foundation models
Proven experience leading or mentoring technical research teams
Strong intuition for model behavior and alignment challenges
Experience designing evaluation systems
PhD or equivalent depth of industry research experience in ML, RL, AI, or related field
Strong publication record at leading ML or AI venues
Familiarity with large-scale training infrastructure and compute trade-offs

Principal AI Research Scientist – Post-Training, Alignment, Reinforcement Learning

Key skills