xAI is seeking a Post-Training Engineer to enhance the instruction-following capability and general usefulness of pre-trained models, contributing to the development of AI systems that understand the universe and create new knowledge.
Responsibilities
Creating and driving agendas to advance model quality
Improving data mixtures by building data collection pipelines
Developing data generation techniques
Creating generalizable reward models
Developing reinforcement learning algorithms
Designing and implementing robust model evaluations
Designing and implementing large-scale model training frameworks
Collaborating with other teams to push model capability frontiers
Requirements
Expert in ML and fine-tuning large language models
Track record in leading studies impacting AI advancement
Experience in data-driven large language model behavior improvements
Experience in reinforcement learning or inference-time search techniques
Experience in developing benchmarks or distributed machine learning systems
Experience in model optimizations under complex setups