Applied Scientist, RL post-training, AWS
Core
Develop Reinforcement Learning (RL) post-training solutions for frontier Large Language Models (LLMs) to enhance instruction following, reasoning over long context, and tool use for customer service applications.
Role type
Senior Applied Scientist (RL & LLM Post-training)
Builds
Advanced LLM capabilities and post-training pipelines for AWS cloud services
Domain
Cloud computing, Artificial Intelligence, Reinforcement Learning, Large Language Models
Deliverable
production ML models
Required skills
PhD or Master's with 6+ years applied research, Neural deep learning methods, Machine learning, Python/C++/Java programming
Preferred skills
LLM post-training research, Top-tier AI conference publications (NeurIPS, ICML, ACL), MxNet, TensorFlow
Technologies
Python, C++, Java, MxNet, TensorFlow, LLMs, RL algorithms
Responsibilities
Develop innovative RL post-training solutions for LLMs, Partner with technology and business teams to solve real-world problems, Publish findings at peer-reviewed conferences and journals
Seniority
Senior, hands-on IC with research leadership