Senior Reinforcement Learning Engineer - Large Language Models

poolside is seeking a Senior Reinforcement Learning Engineer to work on Large Language Models. You will develop and optimize RL algorithms for training and fine-tuning LLMs, collaborate with a world-class team, and contribute to advancing AGI.

• Design and implement reinforcement learning algorithms for large language models.
• Optimize training pipelines and improve model performance.
• Collaborate with researchers and engineers to push the boundaries of AGI.

• Strong background in reinforcement learning and deep learning.
• Experience with large language models.
• Proficiency in Python and PyTorch.
• PhD or equivalent experience.

• Experience with distributed training, transformers, and RLHF.
• Familiarity with LLM alignment techniques.