Job Summary
This role involves leading comprehensive full-stack machine learning experiments, specifically focusing on training reward models, classifiers, and verifiers in nuanced subjective domains. As part of your responsibilities, you will create innovative evaluations and benchmarks while working closely with AI laboratories and creative professionals.
Responsibilities
- Oversee the execution of full-stack machine learning experiments.
- Develop and train reward models, classifiers, and verifiers specifically for subjective applications.
- Create advanced evaluations and benchmarks for performance assessment.
- Collaborate effectively with AI labs and creative experts to drive innovative solutions.
Qualifications
- Extensive experience in post-training evaluations and working with large language models (LLMs).
- Preference for candidates with previous startup experience.
- Strong engineering execution skills paired with a researcher’s analytical mindset.
- A genuine passion for design and creativity in machine learning applications.
