Research Engineer (Agentic EDA)

Normal Computing; Denmark; On-site; DKK 1,200,000 - 1,600,000; Full time

Job summary

Normal Computing is seeking a Research Engineer to push the frontier of agentic LLMs and reinforcement learning for advancing our agentic AI platform in semiconductor design automation. You will design and run experiments, build agents, curate datasets from complex technical artifacts, and create rigorous evaluations.

You’ll write production-quality research code and work closely with engineering to ship improvements to customers, building prototypes that integrate with production code

Qualifications

• PhD in CS/AI/ML or equivalent research experience.
• Publications in multi-agent RL / agentic AI preferred.
• Experience turning research into production systems.
• Strong Python and ML framework experience (PyTorch preferred; JAX/HF a plus).
• Familiarity with EDA tools and semiconductor domains is a plus.

Responsibilities

• Build multi-agent systems for code generation that interact with EDA tools.
• Design experiments, run evaluations, and publish results.
• Develop RL environments and reward models.
• Collaborate with engineering to productionize results.
• Create research prototypes that integrate with production agentic code generation tool.

Skills

Python

ML Frameworks

Research to Production

Communication

Education

PhD in CS/AI/ML (or equivalent)

Tools

PyTorch

JAX

Transformers

RLlib

HF

Job description

• We’re hiring a Research Engineer to push the frontier of agentic LLMs and reinforcement learning for pushing the capabilities of Normal EDA, our agentic AI platform for semiconductor design automation. You’ll design and run experiments, build agents, curate datasets from complex technical artifacts, and create rigorous evaluations. You’ll write production-quality research code and work closely with engineering to ship improvements to customers
• Build multi-agent systems for code generation that interact with EDA tools (e.g., simulations, waveform analysis, formal tools, physical design tools), propose fixes, and iterate through all stages of chip design and verification flows
• Build research prototypes that integrate with our production agentic code generation tool; collaborate to productionize wins
• Create RL environments and evaluations for agents, explore proxy rewards and consider speed/accuracy tradeoffs of custom tools
• Generate datasets from silicon collateral (e.g., RTL, testbenches, custom VIPs) sources such as RTL designs/VIPs/chip specifications/agent logs; generate synthetic data where appropriate; maintain data cards and licensing
• Analyze experiments with disciplined ablations; document results and drive progress with technical rigour
• Stay current on LLM agents, RL (offline/online, RLHF/RLAIF), constrained decoding, and program synthesis

• Strong Python and ML framework experience (PyTorch preferred; JAX/HF a plus)
• Experience designing evaluation environments and reward models for sequential/agentic tasks
• Clear communicator who partners well with other engineers
• Comfortable with data acquisition/curation; good instincts about data quality and licenses
• Experience and fluency with EDA tools (formal, simulation, physical design)
• PhD in CS/AI/ML (or equivalent research experience) with publications ideally in multi-agent RL, agentic AI, or RL for language/code
• Demonstrated ability to turn research into working systems
• Research on program synthesis/codegen, constrained decoding, or execution-based rewards
• Experience with offline RL from tool traces or human corrections
• Open-source contributions (e.g., SkyRL, verl, RLlib, Transformers, Pytorch)
• Familiarity with semiconductor/chip domains or other complex technical domains
• Track record of shipping research to production