Senior Machine Learning Engineer, Model Training and Reinforcement Learning

Nebius is seeking a Senior Machine Learning Engineer to own the infrastructure for large-scale AI model training and reinforcement learning experiments. This role involves designing and implementing training and RL pipelines, building supporting data and systems, and delivering measurable improvements in model quality and reliability.

• Design and run model-training and post-training experiments (SFT, DPO, RLHF)
• Build reward functions, judge models, and evaluation sets
• Create synthetic data and data pipelines
• Build and maintain distributed training and RL infrastructure
• Profile and improve GPU utilization and training throughput
• Design rigorous evaluations for model capabilities and safety