System Software Engineer - Performance Verification Infrastructure

NVIDIA Gruppe; Bengaluru; Hybrid; INR 2,800,000 - 4,200,000; Full time

Job summary

NVIDIA Bengaluru is seeking a skilled software engineer to join the GPU Performance Infrastructure team. You will help validate and ship next-generation GPU architectures, building pipelines, dashboards, and tooling to measure and compare performance across builds and environments.

The role emphasizes C++ and Python expertise, strong CS fundamentals, and collaboration with GPU architects and HW teams to accelerate verification and drive cutting-edge GPU performance improvements.

Qualifications

• BS/MS in CS/CE or equivalent experience.
• 3+ years software engineering experience, primarily in C++, with Python for tooling and automation.
• Strong CS fundamentals, including data structures, algorithms, OOP, and system design.
• Full-stack experience with backend (Java/Python), REST APIs, and modern frontend (React/Ember) for data-intensive applications is a plus.
• Proficiency in databases (SQL, MongoDB) for metrics storage and querying is a plus.
• Hands-on experience with Git, CI/CD, Kubernetes, Docker, and messaging systems (RabbitMQ) is a plus.
• Exposure to GPU/CPU/SoC chip performance verification is a plus.
• Familiarity with AI development tools.
• Excellent interpersonal skills.

Responsibilities

• Design and maintain automated chip performance verification pipelines spanning workload trace generation, multi-target test execution, results post-processing, and correlation with architectural performance targets.
• Develop performance monitoring and measurement infrastructure that provides consistent observability across simulation, emulation, and silicon environments.
• Build scalable data pipelines and full-stack dashboards to ingest, visualize, and compare performance metrics across builds and environments.
• Coordinate with GPU architects to craft infrastructure for performance verification of upcoming architectures.
• Work closely with HW teams to automate and accelerate verification workflows, enabling faster GPU build iteration.
• Empower GPU architects by providing insights to understand current performance and model industry-leading performance for future builds.
• Improve the daily workflows of the world's top chip architects, contributing to the creation of the next greatest generation of GPUs!

Skills

C++

Python

Data structures & algorithms

OOP

Education

BS/MS in Computer Science or Computer Engineering

Tools

Git

CI/CD

Kubernetes

Docker

RabbitMQ

Job description

NVIDIA has been transforming computer graphics, PC gaming, and accelerated computing for more than 25 years. It’s a unique legacy of innovation that’s fueled by great technology—and amazing people. Today, we’re tapping into the unlimited potential of AI to define the next era of computing. An era in which our GPU acts as the brains of computers, robots, and self-driving cars that can understand the world. Doing what’s never been done before takes vision, innovation, and the world’s best talent. As an NVIDIAN, you’ll be immersed in a diverse, supportive environment where everyone is inspired to do their best work. Come join the team and see how you can make a lasting impact on the world.

Join NVIDIA's GPU Performance Infrastructure team and be part of a brand-new journey in validating and shipping next-generation GPU architectures. At NVIDIA, we empower our engineers to innovate and drive powerful performance through innovative infrastructure and workflows. This role is uniquely positioned to influence the entire lifecycle of GPU performance verification, from early-stage modelling to post-silicon validation. With our bold standards and extraordinary team, you'll have the chance to define a significant impact on the future of computing!

What you'll be doing:

• Design and maintain automated chip performance verification pipelines spanning workload trace generation, multi-target test execution, results post-processing, and correlation with architectural performance targets.
• Develop performance monitoring and measurement infrastructure that provides consistent observability across simulation, emulation, and silicon environments.
• Build scalable data pipelines and full-stack dashboards to ingest, visualize, and compare performance metrics across builds and environments.
• Coordinate with GPU architects to craft infrastructure for performance verification of upcoming architectures.
• Work closely with HW teams to automate and accelerate verification workflows, enabling faster GPU build iteration.
• Empower GPU architects by providing insights to understand current performance and model industry-leading performance for future builds.
• Improve the daily workflows of the world's top chip architects, contributing to the creation of the next greatest generation of GPUs!

What we need to see:

• BS/MS in Computer Science, Computer Engineering, or equivalent experience.
• 3+ years of software engineering experience, primarily in C++, with Python for tooling and automation.
• Strong CS fundamentals, including data structures, algorithms, OOP, and system design.
• Full-stack experience with backend (Java/Python), REST APIs, and modern frontend (React/Ember) for data-intensive applications is a plus.
• Proficiency in databases (SQL, MongoDB) for metrics storage and querying is a plus.
• Hands-on experience with Git, CI/CD, Kubernetes, Docker, and messaging systems (RabbitMQ) is a plus.
• Exposure to GPU/CPU/SoC chip performance verification is a plus.
• Familiarity with AI development tools.
• Excellent interpersonal skills.

#LI-Hybrid