About me
I’m a PhD student in Computer Science and Engineering at The Ohio State University, advised by Andrew Perrault. I work on AI safety and alignment: how LLMs make decisions under trade-offs, against other agents, and under chance, and what post-training, especially reinforcement learning, changes about that.
Before Ohio State, I earned my B.Sc. in Electrical Engineering at the University of Tehran.
I’m looking for Summer 2027 research internships in RL, post-training, and LLM agents.
Research Interests
- RL for LLM agents: multi-turn and agentic RL, credit assignment
- Self-play and game-based RL for LLMs, and what transfers from it
- Multi-objective and constrained RLHF
- LLMs in strategic, multi-agent, and stochastic settings
- How post-training affects safety, and the trade-offs between safety and capability
