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

This is a fully remote position, open to applicants in California, +3 more states.

📋 Description

• Conduct post-training activities for model development.

• Create innovative algorithms aimed at enhancing model reliability, controllability, and alignment.

• Design and execute experiments that influence model behavior.

• Collaborate with infrastructure teams to establish scalable and reproducible workflows.

• Contribute to publications, patents, and enhance visibility in external research.

• Lead human-in-the-loop evaluations ensuring high-quality annotations.

• Clearly communicate technical risks, limitations, and trade-offs to leadership.

⛳️ Requirements

• Extensive hands-on experience in reinforcement learning specifically for foundation models.

• Demonstrated experience in leading or mentoring technical research teams.

• Strong intuition regarding model behavior and the challenges of alignment.

• Experience in designing evaluation systems.

• PhD or equivalent industry research experience in ML, RL, AI, or a related discipline.

• Strong track record of publications in prominent ML or AI venues.

• Familiarity with large-scale training infrastructure and understanding of compute trade-offs.

🏝️ Benefits

• Health insurance coverage.

• Flexible work arrangements available.

• Opportunities for professional development.