Architect – AI-Powered Performance Verification Automation

About NVIDIA

Role Overview

Responsibilities

• Build AI/ML tools that generate, triage, and analyze performance test cases and results.
• Develop intelligent agents for regression detection, root-cause analysis, and corrective-action recommendations.
• Integrate LLM assistants into verification infrastructure for natural-language data and specification queries.
• Create data pipelines for verification-data collection, curation, labeling, and model improvement.
• Partner with verification engineers to define priorities and validate solutions against real workflows.
• Create dashboards measuring cycle time, coverage, and productivity improvements.
• Stay current with generative AI, reinforcement learning, and formal methods for verification.

Required Qualifications

• B.Tech, M.Tech, or PhD in Electrical Engineering, Computer Science, or a related field.
• 3+ years of experience in hardware verification, performance validation, or EDA tool development.
• Strong Python programming skills.
• Hands-on experience with ML/AI frameworks or LLM APIs.
• Understanding of benchmarking, profiling, and regression analysis for performance verification.
• Experience with CI/CD pipelines and infrastructure automation.

Preferred Qualifications

• Familiarity with C/C++ or SystemVerilog/UVM is a plus.
• Experience applying ML to EDA or verification problems is preferred.
• Familiarity with RAG architectures, prompt engineering, and agentic AI frameworks is preferred.
• Knowledge of NVIDIA GPU/SoC architecture or similar complex hardware platforms is preferred.
• Published work or patents in AI-for-verification or related domains are preferred.