Researcher, Post Training

About the role

Cartesia is building AI that learns and interacts like humans. The Post‑Training team is focused on making multimodal models adaptive, aligned, and grounded in human intent. As a Researcher you will work at the intersection of machine‑learning research, alignment, and infrastructure, creating new techniques for preference optimization, model evaluation, and feedback‑driven learning.

Key responsibilities

• Own research initiatives to improve alignment and capabilities of multimodal models.
• Develop new post‑training methods and evaluation frameworks to measure model improvement.
• Partner closely with research, product, and platform teams to define best practices for specialized models.
• Implement, debug, and scale experimental systems to ensure reliability and reproducibility across training runs.
• Translate research findings into production‑ready systems that enhance model reasoning, consistency, and human alignment.

Required profile

• Deep knowledge of preference optimization and alignment methods, including RLHF.
• Experience designing evaluations and metrics for generative or multimodal models.
• Strong engineering and debugging skills with experience building or scaling complex ML systems.
• Ability to trace and diagnose complex behaviors in model performance across training and evaluation pipelines.

Required skills

• Preference optimization
• RLHF (Reinforcement Learning from Human Feedback)
• Multimodal model evaluation
• ML systems engineering

What we offer

• Competitive base salary with an attractive equity package.
• Fully covered medical, dental, and vision insurance for you and your family.
• Parental leave: 9 weeks paternity, 12 weeks maternity.
• 401(k) retirement plan.
• Monthly commuter allowance.
• Flexible PTO to recharge as needed.
• Daily meals and snacks provided.