Systems Engineer, World Model Evaluation - Autonomous Vehicles

NVIDIA Corporation; Santa Clara (CA); On-site; USD 184,000 - 357,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA is seeking an experienced systems engineer to advance world-model evaluation for autonomous driving. You will translate driving-feature needs into measurable requirements, create scenarios, and build evaluators linking perception and map-fusion to vehicle behavior.

Collaborate across perception, mapping, planning, safety, and data teams to ensure robust evaluation and release readiness. The role emphasizes Python/SQL expertise, data-driven decision making, and creating scalable evaluation

Qualifications

• MS or PhD in engineering, computer science, physics, data science or related field, or equivalent experience.
• 8+ years of relevant experience in systems engineering, quantitative systems analysis, verification and validation, data science or experiment design for complex software systems.
• Experience translating system needs and failure modes into measurable requirements, test strategies and acceptance criteria.
• Experience evaluating perception, map-fusion or comparable systems, including evaluation-data strategies and ground-truth quality.
• Strong Python and SQL skills, with experience building reproducible analyses and extracting insights from large datasets.
• Experience building Python evaluation pipelines using distributed data-processing frameworks, object storage and SQL-based data platforms.
• A foundation in statistical analysis, experiment design, measurement uncertainty and performance-budget allocation.
• Attention to detail and ownership: you check assumptions, validate results and follow issues through to resolution.
• Ability to build technical alignment across teams and communicate findings, limitations and trade-offs clearly.
• Proficiency with SQL and Python or C++

Responsibilities

• Translate driving-feature needs and safety analysis into world-model requirements, performance targets and error budgets.
• Investigate real-world failure modes and develop metrics, scenarios and tests that expose gaps across operating conditions.
• Build and validate evaluators that connect world-model errors to vehicle behavior.
• Partner with our data and ground-truth teams to define evaluation datasets and labeling guidelines, addressing ambiguous cases, label quality, coverage, provenance and independence from training data.
• Develop reproducible analysis and automated triage using on-road data, replay and closed-loop simulation to distinguish product failures from evaluation and data issues.
• Help us turn results into decisions through evaluation tools and dashboards that guide improvements and demonstrate release readiness.

Skills

Python

SQL

C++

Data analysis

Systems engineering

Education

MS or PhD in Engineering / CS / Physics / Data Science or related

Tools

Temporal

SQL-based data platforms

Python pipelines

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.

Help us measure how accurately autonomous vehicles understand the world! We’re looking for an experienced systems engineer to join NVIDIA’s autonomous-driving systems engineering team and advance our world-model evaluation capabilities, connecting perception and map-fusion performance to driving behavior and safety. How do we know whether the vehicle’s representation of its surroundings is accurate, and which failures do our tests miss? Together, we’ll develop requirements, metrics and evaluations that uncover gaps and guide engineering improvements. You’ll collaborate with our perception, mapping, planning, safety and infrastructure teams to turn real-world failures into reliable evidence for development and release decisions.

What you will be doing:

• Work with us to translate driving-feature needs and safety analysis into world-model requirements, performance targets and error budgets.
• Investigate real-world failure modes and develop metrics, scenarios and tests that expose gaps across operating conditions.
• Build and validate evaluators that connect world-model errors to vehicle behavior.
• Partner with our data and ground-truth teams to define evaluation datasets and labeling guidelines, addressing ambiguous cases, label quality, coverage, provenance and independence from training data.
• Develop reproducible analysis and automated triage using on-road data, replay and closed-loop simulation to distinguish product failures from evaluation and data issues.
• Help us turn results into decisions through evaluation tools and dashboards that guide improvements and demonstrate release readiness.

What we need to see:

• MS or PhD in engineering, computer science, physics, data science or a related field, or equivalent experience.
• 8+ years of relevant experience in systems engineering, quantitative systems analysis, verification and validation, data science or experiment design for complex software systems.
• Experience translating system needs and failure modes into measurable requirements, test strategies and acceptance criteria.
• Experience evaluating perception, map-fusion or comparable systems, including evaluation-data strategies and ground-truth quality.
• Strong Python and SQL skills, with experience building reproducible analyses and extracting insights from large datasets.
• Experience building Python evaluation pipelines using distributed data-processing frameworks, object storage and SQL-based data platforms.
• A foundation in statistical analysis, experiment design, measurement uncertainty and performance-budget allocation.
• Attention to detail and ownership: you check assumptions, validate results and follow issues through to resolution.
• Ability to build technical alignment across teams and communicate findings, limitations and trade-offs clearly.
• Proficiency with SQL and Python or C++

Ways to stand out from the crowd:

• Experience evaluating perception, mapping or planning systems in autonomous vehicles, machine learning or computer vision contexts, with the ability to connect subsystem metrics to closed-loop vehicle behavior.
• Strong data science and analytics background, with experience uncovering performance trends, failure patterns and coverage gaps across large datasets and building data-driven dashboards with web interfaces, backend APIs and evaluation visualizations.
• Experience developing and validating evaluation tooling and reproducible workflows, including orchestration frameworks such as Temporal and validation methods for outputs from VLMs, LLMs or agentic triage pipelines.
• Familiarity with automotive functional safety concepts, including fault-tree analysis and failure-rate allocation.
• Software engineering proficiency in C++ and automated testing.

#AutonomousVehicles

Your base salary will be determined based on your location, experience, and the pay of employees in similar positions. The base salary range is 184,000 USD - 287,500 USD for Level 4, and 224,000 USD - 356,500 USD for Level 5.

You will also be eligible for equity and benefits.

Applications for this job will be accepted at least until October 30, 2026.

This posting is for an existing vacancy.

NVIDIA uses AI tools in its recruiting processes.

NVIDIA is committed to fostering an inclusive work environment and proud to be an equal opportunity employer. As we highly value diversity in our current and future employees, we do not discriminate (including in our hiring and promotion practices) on the basis of race, religion, color, national origin, gender, gender expression, sexual orientation, age, marital status, veteran status, disability status or any other characteristic protected by law.

#deeplearning