for model evaluation, and iteratively improving our metrics based on real-world feedback. Strong communication skills..., you will: Write maintainable, efficient, and well-tested code as part of our evaluation libraries. Develop metrics that accurately...
Engine team to bring your research and data pipeline ideas to life Shape the roadmap for how post-training data is used... to supervise the next generation of large language models Conduct experiments for new research ideas in post-training, leveraging...