AI Agent Testing Engineer

Join NVIDIA's team as an AI Agent Testing Engineer. You will be testing NVIDIA AI agents and end-to-end agentic workflows across the NV GPU Platform.

Responsibilities:

• Test NVIDIA AI agents and end-to-end agentic workflows across NV GPU Platform.
• Design and execute functional, integration, end-to-end, reliability, performance, and security tests.
• Develop automated tests and evaluation frameworks for capabilities such as reasoning, tool use, multi-turn interactions, memory, and retrieval.
• Use AI development tools to improve productivity across test planning, test case development, execution, analysis, and automation.
• Validate cloud-native AI service workflows across API endpoints, deployment, invocation, model serving, routing, streaming, autoscaling, cancellation, authorization, observability, and failure recovery.
• Collaborate with development teams to triage issues, perform root-cause analysis, verify fixes, and improve test coverage and quality.

Requirements:

• Currently pursuing a master’s degree in Computer Science, Computer Engineering, Electrical Engineering, or a related field.
• Strong software development potential, with proficiency in Python and shell scripting.
• Familiarity with AI, machine learning, large language models, or AI agent technologies.
• Experience using AI development tools to improve quality and productivity across the end-to-end QA workflow.
• Good knowledge of Linux and software testing methodologies.
• Familiarity with REST API testing and cloud-native service validation.
• Strong problem-solving, communication, and interpersonal skills.
• Fluent written and spoken English.
• A proactive, innovative, and self-motivated attitude with a passion for learning cutting-edge technologies.
• Ability to work full-time, on-site five days per week, for one year.

Preferred Qualifications:

• Experience testing LLM applications, AI agents, or agentic workflows.
• Experience developing AI evaluation or test automation frameworks.
• Knowledge of RAG, tool calls, prompt engineering, or multi-agent systems.
• Experience with Docker, Kubernetes, OpenStack, or other cloud-native technologies; familiarity with Go is a plus.
• Experience with NVIDIA GPU hardware, CUDA, or parallel programming.