Research Engineer, Agentic EDA

Sourced from drjobpro.com

Normal Computing is seeking a Research Engineer to advance agentic LLMs and reinforcement learning for semiconductor design automation. The role involves building multi-agent systems that interact with EDA tools, creating RL environments, and curating high-quality datasets from silicon collateral. You will bridge the gap between academic research and production-grade AI infrastructure.

• Build multi-agent systems for code generation interacting with EDA tools (simulations, formal verification, physical design).
• Create RL environments and evaluations for agents, exploring proxy rewards and speed/accuracy tradeoffs.
• Generate and curate datasets from RTL designs, VIPs, and chip specifications; maintain data cards and licensing.
• Analyze experiments with disciplined ablations and document results to drive technical progress.
• Collaborate with engineering to productionize research prototypes and ship improvements.

• PhD in CS/AI/ML or equivalent research experience with publications in multi-agent RL, agentic AI, or RL for language/code.
• Strong proficiency in Python and ML frameworks (PyTorch preferred; JAX/HF a plus).
• Demonstrated ability to turn research concepts into working systems.