Intern Engineer – RL Post-Training for LLMs
Core
Develop and optimize RL post-training pipelines for LLMs, conduct experiments to improve model performance, and build scalable training systems.
Role type
Intern Researcher (RL Post-Training for LLMs)
Builds
Scalable training, evaluation, and data generation systems for LLMs
Domain
Artificial Intelligence / Large Language Models / Reinforcement Learning
Deliverable
production ML models
Required skills
Reinforcement Learning, Deep Learning, Large Language Models, Transformer architectures, Python, PyTorch, LLM frameworks
Preferred skills
GRPO, reward modeling, VeRL, Hugging Face, DeepSpeed, vLLM, SGLang, domain-specific languages for AI accelerators, distributed training frameworks
Technologies
PyTorch, Hugging Face, DeepSpeed, vLLM, SGLang, VeRL
Responsibilities
Develop and optimize RL post-training pipelines for LLMs, Conduct experiments to improve model performance, reasoning, and alignment, Build scalable training, evaluation, and data generation systems, Collaborate with researchers and engineers on cutting-edge LLM projects, Stay current with advancements in RL, LLMs, and post-training research
Seniority
Intern, Research