Senior Prompt and Benchmark Engineer, Evaluation of World Models at NVIDIA

Santa Clara, California, United States

Apply Now

Not SpecifiedCompensation

Senior (5 to 8 years)Experience Level

Full TimeJob Type

UnknownVisa

AI, Technology, Generative AIIndustries

Requirements

Demonstrated experience with prompt engineering, including crafting, refining, and optimizing prompts
Strong attention to detail in designing natural language questions and formatting structured evaluations
Proven ability to reason about model capabilities, failure modes, and blind spots in real-world generative model deployments
Experience crafting or contributing to benchmarks or evaluation datasets, especially for multimodal or agentic systems
Familiarity with evaluating models via prompting, capturing structured outputs, and comparing across model families
Excellent communication and collaboration skills
A working understanding of how VLMs and foundation models function at inference time, including token-level outputs, autoregressive decoding, and model context windows
10+ years of experience in Machine Learning, NLP, Human-Computer Interaction, or related fields
BS, MS, or equivalent background. Prior experience in AI evaluation, annotation workflows, or research is highly valued

Responsibilities

Develop detailed, domain-specific benchmarks for evaluating world foundation models, especially generation and understanding world models that reason about video, simulation, and physical environments
Use sophisticated prompt engineering techniques to elicit structured, interpretable responses from a variety of foundation models
Build, refine, and maintain question banks, multiple-choice formats, and test suites to support both automated and human evaluation workflows
Employ multiple VLMs in parallel to explore ensemble evaluation methods such as majority voting, ranking agreement, and answer consensus
Make evaluation as automated and scalable as possible by encoding prompts and expected outputs into structured formats for downstream consumption
Interface directly with Cosmos researchers to translate their evaluation needs into scalable test cases
Collaborate with human annotators, providing clearly structured tasks, feedback loops, and quality control mechanisms to ensure dataset reliability
Meet regularly with domain experts in robotics, autonomous vehicles, and simulation to understand their internal benchmarks, derive transferable metrics, and co-develop standardized evaluation formats

Skills

prompt engineering

benchmark development

generative modeling

world models

VLMs

ensemble evaluation

video generation

simulation

autonomous vehicles

robotics

evaluation workflows

question banks

multiple-choice formats

human annotation

NVIDIA

Designs GPUs and AI computing solutions

About NVIDIA

NVIDIA designs and manufactures graphics processing units (GPUs) and system on a chip units (SoCs) for various markets, including gaming, professional visualization, data centers, and automotive. Their products include GPUs tailored for gaming and professional use, as well as platforms for artificial intelligence (AI) and high-performance computing (HPC) that cater to developers, data scientists, and IT administrators. NVIDIA generates revenue through the sale of hardware, software solutions, and cloud-based services, such as NVIDIA CloudXR and NGC, which enhance experiences in AI, machine learning, and computer vision. What sets NVIDIA apart from competitors is its strong focus on research and development, allowing it to maintain a leadership position in a competitive market. The company's goal is to drive innovation and provide advanced solutions that meet the needs of a diverse clientele, including gamers, researchers, and enterprises.

Santa Clara, CaliforniaHeadquarters

1993Year Founded

$19.5MTotal Funding

IPOCompany Stage

Automotive & Transportation, Enterprise Software, AI & Machine Learning, GamingIndustries

10,001+Employees

Benefits

Company Equity

401(k) Company Match

Risks

Increased competition from AI startups like xAI could challenge NVIDIA's market position.

Serve Robotics' expansion may divert resources from NVIDIA's core GPU and AI businesses.

Integration of VinBrain may pose challenges and distract from NVIDIA's primary operations.

Differentiation

NVIDIA leads in AI and HPC solutions with cutting-edge GPU technology.

The company excels in diverse markets, including gaming, data centers, and autonomous vehicles.

NVIDIA's cloud services, like CloudXR, offer scalable solutions for AI and machine learning.

Upsides

Acquisition of VinBrain enhances NVIDIA's AI capabilities in the healthcare sector.

Investment in Nebius Group boosts NVIDIA's AI infrastructure and cloud platform offerings.

Serve Robotics' expansion, backed by NVIDIA, highlights growth in autonomous delivery services.

Land your dream remote job 3x faster with AI

Try Jobo Free