Research Engineer - Language Model Pre-Training

The role

You will shape the language model roadmap through end-to-end pretraining development. You will work on large-scale training runs, performance optimization, dataset processing, and architecture research.

What you will do

• Large-scale training runs and model parallelization
• Performance optimization of the pretraining stack
• Dataset collection, processing, and evaluation
• Architecture and methodology research, including optimizer ablations

Required qualifications

• Strong engineering aptitude for rapidly implementing reliable and robust systems
• Can rapidly learn new fields and are excited to implement new ideas
• Excellent communication and collaboration skills
• Can work effectively on both research and engineering implementation at scale
• Deep expertise and intuition for solving machine learning problems and training models
• Experience with training on large-scale (multi-node) GPU clusters
• Deep understanding of model training pipelines including model/data parallelism and distributed optimizers
• Strong grasp of proper experimental methodology for running rigorous ablations and other hypothesis testing
• Understanding of large-scale, highly parallel data processing pipelines
• High proficiency with PyTorch and Python
• Strong ability to dive into large pre-existing codebases and rapidly get up to speed
• Postgraduate degree in a scientific subject (Computer Science, EE/EECS, Math, Physics)

Nice to have

• Published machine learning research in well-respected venues

Benefits

• Comprehensive medical, dental, vision, and FSA plans
• Competitive compensation and 401(k) plan
• Relocation and immigration support on a case-by-case basis
• In-office snacks and meals provided
• Unlimited PTO and company holidays

About the company

Zyphra is an artificial intelligence company based in San Francisco, California.