Researcher, Post Training

Job summary

Responsibilities

The next leap in model intelligence won’t come from scale alone — it will come from better post-training and alignment. Cartesia’s Post-Training team is developing the methods and systems that make multimodal models truly adaptive, aligned, and grounded in human intent.

• Own research initiatives to improve the 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 creating 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

What they're looking for

• 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 the training and evaluation pipeline

Tech stack

• Databricks