About Me
Chief Scientist at Tzafon, working on reinforcement learning, continual learning, and scaling infrastructure for large language models.
Previously, I was a Postdoctoral Researcher at the ETH AI Center, contributed to SwissAI, and worked at Google DeepMind. I received my Ph.D. from the Technion, where my research focused on distributed neural network training.
Focus
-
Reinforcement learning
Scaling RL post-training with verifiable rewards and efficient policy optimization.
-
Continual learning
Helping agents learn from experience, retain skills, and adapt over time.
-
LLM systems
Building scalable training and inference infrastructure for large models.
Contact
I'm best reached via email. I'm always open to interesting conversations and collaboration opportunities.