Architect – AI-Powered Performance Verification Automation
RemoteFull-time3–6 yrsPosted 2 months ago
Mid-level AI role at Nvidia. Needs 3+ years and a B.Tech, B.E. or M.Tech. Remote.
About the role
You will get to work on high performance CPU and Memory sub-systems, Next-Gen GPUs , NOC based Interconnect Fabric etc. Make the choice to join us today. We are looking for a motivated engineer to drive the transformation of performance verification workflows through AI and automation.
What you'll do
- Automate verification workflows by building AI/ML-based tools that generate, triage, and analyse performance test cases and results
- Develop intelligent agents that can identify performance regressions, root-cause failures, and recommend corrective actions
- Integrate LLM-based assistants into existing verification infrastructure to enable natural-language querying of results, specs, and coverage data
- Design data pipelines to collect, curate, and label verification data for model training and continuous improvement
- Collaborate with verification engineers to understand pain points, define automation priorities, and validate AI-driven solutions against real-world workflows
What you need
- Machine learning
- Scikit-learn
- LLMs
- ETL
- PyTorch
- TensorFlow
Good to have
- Python
- Prompt engineering
- C++
- UVM
- C
- Verilog