Senior ML-Driven DFX Software Engineer

NVIDIA Corporation; Santa Clara (CA); On-site; USD 170,000 - 288,000; Full time

Job summary

NVIDIA seeks a Senior DFX Software Engineer for Machine Learning in Santa Clara, CA. You will develop high-performance software for test pattern generation, silicon testing, and failure analysis, and you will implement advanced graph analytics and ML approaches.

Collaboration across teams is essential to tackle cross-disciplinary challenges. The role involves applying LLMs, GNNs, and reinforcement learning to design innovative EDA solutions, with emphasis on scalable, concurrent architectures

Qualifications

• BS in EE or CS (or equivalent experience).
• MS or higher degree preferred.
• 5+ years of software development experience.
• Strong programming in Python or C++, hands-on in modern C++.
• Experience with LLMs, GNNs, and reinforcement learning for EDA solutions.
• Expertise in high-performance algorithms for DFT, simulations, and failure analysis.
• Understanding of agent architectures, RAG systems, and communication protocols.
• Familiarity with PPO/SAC/Q-learning and hyperparameter tuning.

Responsibilities

• Develop high-performance software for test pattern generation, silicon testing, failure analysis, and yield learning.
• Create efficient parallel graph traversal and graph analysis techniques.
• Collaborate with multi-functional teams to tackle cross-disciplinary problems.
• Apply LLMs, RAGs, graph-based ML, and reinforcement learning to define innovative solutions.

Skills

Python

C++

LLMs

GNNs

Reinforcement Learning

Education

B.S. in EE or CS

MS or higher preferred

Tools

Spark

Job description

NVIDIA seeks a Senior DFX Software Engineer for Machine Learning in Santa Clara, CA. You will develop high-performance software for test pattern generation, silicon testing, and failure analysis, and you will implement advanced graph analytics and ML approaches.

Collaboration across teams is essential to tackle cross-disciplinary challenges. The role involves applying LLMs, GNNs, and reinforcement learning to design innovative EDA solutions, with emphasis on scalable, concurrent architectures