Architect, AI-Powered Performance Verification Automation at NVIDIA (Bengaluru, Pune, Hyderabad, Gurugram or Remote)
Job Description
NVIDIA is hiring an Architect for AI-powered performance verification automation, based in Bengaluru, Gurugram, Hyderabad or Pune, or remote in India, to rebuild how GPU and SoC performance verification is done using machine learning, LLM assistants and intelligent agents.
At a glance
- Role: Architect – AI-Powered Performance Verification Automation
- Location: Bengaluru, Gurugram, Hyderabad, Pune or remote in India
- Experience: 3+ years in hardware verification, performance validation or EDA tool development
- Focus: AI/ML tools and agents for hardware performance verification
- Requisition: JR2024489
- Apply: open until filled (re-checked 12 October 2026)
What you will do
- Build AI/ML tools that generate, triage and analyse performance test cases and results
- Develop agents that spot performance regressions, root-cause failures and recommend fixes
- Integrate LLM assistants into verification infrastructure for natural-language queries over results, specs and coverage
- Design data pipelines to collect, curate and label verification data for model training
- Work with verification engineers to prioritise automation and validate AI tools on real workflows
- Set up metrics and dashboards for cycle-time, coverage and productivity gains, and track research in generative AI, reinforcement learning and formal methods
Performance verification checks that a chip design meets its speed targets before and after silicon, and it involves large amounts of repetitive test generation and triage. The posting describes replacing much of that manual analysis with self-improving automation across CPU and memory subsystems, next-generation GPUs and network-on-chip fabrics.
What NVIDIA is looking for
- A B.Tech, M.Tech or PhD in electrical engineering, computer science or a related field
- 3+ years in hardware verification, performance validation or EDA tool development
- Strong Python (C/C++ and SystemVerilog/UVM a plus)
- Hands-on experience with PyTorch, TensorFlow, scikit-learn or LLM APIs (OpenAI, NVIDIA NIM/NeMo)
- Understanding of performance verification methods such as benchmarking, profiling and regression analysis
- Experience with CI/CD pipelines and infrastructure automation
Nice to have
- Applying ML to EDA or verification (coverage closure, bug prediction, test generation)
- RAG, prompt engineering and agent frameworks such as LangChain or CrewAI
- Knowledge of NVIDIA GPU/SoC or similar architectures
- Publications or patents in AI for verification
Pay and location
NVIDIA’s posting does not state a salary. It lists Bengaluru, Gurugram, Hyderabad and Pune, and remote work within India.
How to apply
Apply through the official NVIDIA job posting. NVIDIA’s posting does not give a closing date, so the role is open until filled; ResearchJobs.in will re-check this listing on 12 October 2026. Check the posting for location and work-authorisation details before you apply.
See all our artificial intelligence jobs, or browse more research jobs on ResearchJobs.in.
Hiring institution: NVIDIA
Official advertisement: nvidia.wd5.myworkdayjobs.com
How to prepare for this application
- Verification basics: be ready to explain how performance tests and regressions are tracked on a chip project.
- ML for EDA: read about ML for coverage closure and test generation.
- Agents: sketch an agent that triages a failing regression and proposes a root cause.
- Data: think about labelling verification logs for model training.
- Impact metrics: prepare numbers from automation you built before.
About NVIDIA
NVIDIA, headquartered in Santa Clara, California, designs graphics processing units (GPUs) and accelerated computing platforms used for AI, graphics, scientific computing, autonomous vehicles and robotics. Its DRIVE, Jetson and IGX platforms, mentioned in several of its India roles, target cars, robots and industrial edge systems. NVIDIA has large engineering teams in India, with offices in Bengaluru, Pune, Hyderabad and Gurugram.
