Researcher, Post Training

Highlights

• Develop post-training methods that make multimodal models adaptive and aligned.
• Build feedback-driven learning systems to improve reasoning across modalities.
• Shape how Cartesia foundation models learn, improve and connect with people.

What they offer

• Competitive base salary and equity package
• Fully covered medical, dental and vision insurance for you and family
• 9 weeks paternity and 12 weeks maternity leave
• 401(k)
• Monthly commuter allowance
• Flexible PTO
• Daily lunch, dinner and snacks

Ideal candidate

ML researcher passionate about alignment and multimodal intelligence who thrives at the intersection of research and engineering and wants to translate novel post-training ideas into real-world models.

Requirements

• Deep knowledge of preference optimization and alignment methods, including RLHF and related approaches
• 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 pipeline