Kevin Luzbetak

Kevin Thomas Luzbetak, MSc, AI/ML Engineer

AI/ML Software Engineer — Applied LLM / RAG systems, AI agents, and production data platforms.

Education
Master of Science, Artificial Intelligence (2014)
Location
Los Angeles, California
GitHub
github.com/luzbetak
Email
Luzbetak5739@gmail.com
Artificial Intelligence (AI) green= components used in RAG · click any topic to open its page Search & Planning Uninformed (BFS, DFS) Shortest Path (Dijkstra, A*) Adversarial (Minimax, MCTS) Constraint Satisfaction Knowledge & Reasoning Expert Systems Rule-based Systems Knowledge-based Systems Knowledge Graphs Logic & Inference Bayesian Networks Fuzzy Logic Natural Language Processing (NLP) Tokenization Text Classification Named Entity Recognition (NER) Sentiment Analysis Machine Translation Summarization Question Answering Information Retrieval (BM25, TF-IDF) Speech (ASR, Text-to-Speech) Transformer Architecture Self-Attention Encoder-Only (BERT, RoBERTa) Embedding Models ← RAG embeddings MiniLM (384 dims) multi-qa-mpnet (768 dims) OpenAI ada-002 (1536 dims) Decoder-Only (GPT, Claude, LLaMA) Large Language Models (LLMs) Mixture of Experts (MoE) Encoder-Decoder (T5, BART) Vision Transformers (ViT) Robotics Perception & SLAM Control Algorithms Path Planning (A*, Dijkstra) LLM Engineering Prompt Engineering Retrieval-Augmented Generation (RAG) Vector Search (FAISS, pgvector) Hybrid Search & Reranking Agents & Tool Use (MCP) Function Calling / Structured Output Orchestration (LangGraph, DSPy) Fine-tuning (LoRA, RLHF) Serving & Quantization (vLLM) Evaluation (RAGAS) LLMOps LLM Security (OWASP) Computer Vision Image Classification Object Detection Image Segmentation Facial Recognition Document AI & OCR Medical Imaging Vision-Language (CLIP) Vision Services (Azure AI) Generative Models Autoencoders Variational Autoencoders (VAE) Generative Adversarial Networks (GAN) DCGAN StyleGAN CycleGAN Diffusion Models Stable Diffusion DALL-E Midjourney Autoregressive (GPT-style) Evolutionary Computation Genetic Algorithms Swarm Intelligence Deep Learning (DL) Feedforward Neural Networks (FNN) Perceptron Multi-Layer Perceptron (MLP) Convolutional Neural Networks (CNN) ResNet / EfficientNet YOLO (Object Detection) Recurrent Neural Networks (RNN) Vanilla RNN LSTM (Long Short-Term Memory) Bidirectional LSTM Stacked LSTM GRU (Gated Recurrent Unit) Graph Neural Networks (GNN) Graph Convolutional Networks (GCN) Graph Attention Networks (GAT) Transformers (see above) Frameworks PyTorch Keras / TensorFlow Hugging Face Machine Learning (ML) Supervised Learning Classification Logistic Regression Decision Trees Random Forest Support Vector Machines (SVM) Naive Bayes K-Nearest Neighbors (KNN) Regression Linear Regression Polynomial Regression Ridge / Lasso Regression Ensembles Bagging (Random Forest) Gradient Boosting (XGBoost, LightGBM) Unsupervised Learning Clustering K-Means DBSCAN Hierarchical Clustering Dimensionality Reduction PCA (Principal Component Analysis) t-SNE UMAP Anomaly Detection Semi- / Self-Supervised Learning Reinforcement Learning Q-Learning / DQN Policy Gradient (PPO) RLHF Time-Series Forecasting Recommender Systems Tooling scikit-learn