Researcher, Post Training
Researcher, Post Training
Researcher, Post Training
Cartesia
Cartesia is a pioneering AI company focused on developing next-generation models that can process and reason over extensive streams of audio, video, and text. The Researcher role in the Post-Training team involves enhancing multimodal models through innovative techniques in preference optimization and alignment, contributing to the company's mission of creating interactive intelligence.
Qualification
- 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
Responsibility
- 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
