Software Engineer Intern

As a Software Engineer Intern at NVIDIA, you will join the PerfLab team and work on cutting-edge projects that involve integrating AI into testing and service workflows. You will collaborate with leading experts to develop tools and technologies that improve troubleshooting, result analysis, and reporting. Responsibilities: Integrate AI into testing and service workflows to improve troubleshooting, result analysis, and reporting Develop an MCP tool to analyze service logs Create an AI Agent to orchestrate troubleshooting, automate triage, and support root cause analysis across multiple services Build AI-assisted analysis of test results to identify performance regressions, anomalies, and trends across game builds, drivers, and hardware configurations Connect AI analysis with historical results and known issues to provide context and supporting evidence Generate clear, actionable summaries and integrate their delivery into reports, dashboards, and notifications for end-users Collaborate with testing engineers and customers to evaluate AI-generated findings and improve their accuracy and usefulness Implement observability and feedback loops for safe operation in production Propose new architectures and approaches Requirements: Currently pursuing a Bachelor's or Master's degree in Computer Science, Engineering, AI, Data Science, or related field Strong programming fundamentals, especially in Python or TypeScript Solid understanding of data structures, algorithms, and API design Basic knowledge of machine learning concepts, especially retrieval-based or agent-based architectures Familiarity with Git, databases, and data pipelines Strong problem-solving skills and eagerness to learn new technologies Interest in applying AI to performance testing, data analysis, and customer-facing workflows Strong collaboration and communication skills, with the ability to learn quickly and work effectively in a dynamic environment Preferred Qualifications: Strong experience with Python and TypeScript Exposure to LLM evaluation, structured outputs, or human-in-the-loop review workflows Experience with performance testing or test automation, and familiarity with gaming performance metrics and analysis methods Experience with RAG pipelines, vector databases, embeddings, or LLM orchestration Knowledge of containerization and orchestration Job Data by YubHub .