NVIDIA-Certified Associate - Generative AI LLMs

NCA-GENL - NVIDIA-Certified Associate - Generative AI LLMs (opens in a new tab)

Practice Questions with Answers

Exam Blueprint

Study Guide

Topic Areas% of Exam
Core Machine Learning and AI Knowledge30%
Data Analysis14%
Experimentation22%
Software Development24%
Trustworthy AI10%

Core Machine Learning and AI Knowledge

Knowledge of algorithms, conventions, and techniques that allow computers to learn from and make predictions or decisions based on data.
1.1 Assist in deployment and evaluation of model scalability, performance, and reliability under the supervision of senior team members.
1.2 Awareness of the process of extracting insights from large datasets using data mining, data visualization, and similar techniques.
1.3 Build LLM use cases such as retrieval-augmented generation (RAG), chatbots, and summarizers.
1.4 Curate and embed content datasets for RAGs.
1.5 Familiarity with the fundamentals of machine learning (e.g., feature engineering, model comparison, cross validation).
1.6 Familiarity with the capabilities of Python natural language packages (spaCy, NumPy, vector databases, etc.).
1.7 Read research papers (articles, conference papers, etc.) to identify emerging LLM trends and technologies.
1.8 Select and use models to create text embeddings.
1.9 Use prompt engineering principles to create prompts to achieve desired results.
1.10 Use Python packages (spaCy, NumPy, Keras, etc.) to implement specific traditional machine learning analyses.

Data Analysis

Inspecting, cleansing, transforming, and modeling data with the goal of discovering useful information, informing conclusions, and supporting decision-making.
2.1 Awareness of the process of extracting insights from large datasets using data mining, data visualization, and similar techniques.
2.2 Compare models using statistical performance metrics, such as loss functions or proportion of explained variance.
2.3 Conduct data analysis under the supervision of a senior team member.
2.4 Create graphs, charts, or other visualizations to convey the results of data analysis using specialized software.
2.5 Identify relationships and trends or any factors that could affect the results of research.

Experimentation

The study of how to perform, evaluate, and interpret experiments, including AI model evaluation and the use of human subjects in labeling or reinforcement learning from human feedback (RLHF).
3.1 Awareness of the process of extracting insights from large datasets using data mining, data visualization, and similar techniques.
3.2 Compare models using statistical performance metrics, such as loss functions or proportion of explained variance.
3.3 Conduct data analysis under the supervision of a senior team member.
3.4 Create graphs, charts, or other visualizations to convey the results of data analysis using specialized software.
3.5 Identify relationships and trends or any factors that could affect the results of research.

Software Development

Create, maintain, and test software.
4.1 Assist in the deployment and evaluations of model scalability, performance, and reliability under the supervision of senior team member.
4.2 Build LLM use cases such as RAGs, chatbots, and summarizers.
4.3 Familiarity with the capabilities of Python natural language packages (spaCy, NumPy, vector databases, etc.).
4.4 Identify system data, hardware, or software components required to meet user needs.
4.5 Monitor functioning of data collection, experiments, and other software processes.
4.6 Use Python packages (spaCy, NumPy, Keras, etc.) to implement specific traditional machine learning analyses.
4.7 Write software components or scripts under the supervision of a senior team member.

Trustworthy AI

Creation and assessment of ethical, energy-conscious, and reliable artificial intelligence systems capable of interpreting and integrating various forms of data, ensuring that they're designed and applied in a manner that's transparent, fair, and verifiable.
5.1 Describe the ethical principles of trustworthy AI.
5.2 Describe the balance between data privacy and the importance of data consent.
5.3 Describe how to use NVIDIA and other technologies to improve AI trustworthiness.
5.4 Describe how to minimize bias in AI systems.

5.1 Describe the ethical principles of trustworthy AI

1. Privacy - Complying With Regulations, Safeguarding Data
  • Federated Learning

NVIDIA FLARE (opens in a new tab)

2. Safety and Security - Avoiding Unintended Harm, Malicious Threats
3. Transparency - Making AI Explainable
4. Nondiscrimination - Minimizing Bias
  • Synthetic datasets
Delta LakeNVIDIA-Certified Professional Agentic AI