Chat with us, powered by LiveChat
Portnov Computer School
AI Engineer Curriculum
1️⃣ Module 1
⏳ ~2 months
🕒 3-hour sessions
📅 2 times per week
Generative AI Prompt Engineering, Python for AI Engineer from beginning, Python Generative AI libraries and integration, Generative AI projects

  • LLM Fundamentals: Explored transformer-based LLMs, including temperature tuning, token limits, and comparing cloud vs. local models.
  • API-Based Interactions: Interacted with LLMs via direct API calls using Python requests and Postman.
  • Prompt Engineering: Implemented zero-shot, few-shot, and chain-of-thought (CoT) prompting techniques.
  • LangChain Basics: Integrated prompts into LangChain workflows to orchestrate multi-step AI tasks.
  • LLM Memory & Agents: Implemented conversational agents with LangChain memory, handling multi-turn interactions.
  • Vector-Based Search (FAISS): Used FAISS to generate and store embeddings, enabling efficient document retrieval.
  • Text Chunking & Ranking: Optimized RAG pipelines for accurate retrieval, experimenting with chunk sizes, metadata, and hybrid ranking (embedding similarity + BM25).
  • Guardrails & Moderation: Developed safeguards for LLM-generated responses (e.g., hallucination detection, toxicity checks).
  • Syntax & Control Flow: Mastered Python fundamentals, including variables, data types (int, float, str, list, dict), loops (for, while), and conditionals (if/else).
  • Functions & Modules: Built reusable code with functions, imported built-in and custom modules (math, random, os), and implemented error handling (try/except).
  • File Handling & Data Processing: Learned to read/write text and CSV files, process structured data using Pandas, and perform statistical computations using NumPy.
  • Hallucination Reduction: Used retrieval-augmented generation (RAG) and reinforcement learning to minimize incorrect LLM outputs.
  • API Interactions: Used the requests library to fetch and parse JSON data from public APIs.
  • Project 1: Developed a complete data processing pipeline handling file input, computation, and structured output.
  • Project 2: Built a prompt-based Q&A bot using a local LLM and LangChain for structured retrieval.
  • Project 3: Created a RAG-powered chatbot that retrieves context-aware answers from a user-defined corpus.
2️⃣ Module 2
⏳ ~2 months
🕒 3-hour sessions
📅 2 times per week
Training and Fine-Tuning Generative AI Models. Deployment, Testing, Cloud usage of Generative AI and LLMs

  • Parameter-Efficient Fine-Tuning (LoRA): Learned LoRA (Low-Rank Adaptation) to fine-tune LLMs with minimal computational overhead.
  • Feature Extraction: Extracted embeddings from pre-trained models for downstream tasks like classification.
  • Local Model Deployment: Hosted fine-tuned models locally via OpenAPI and tested inference endpoints.
  • Generative Adversarial Networks (GANs): Studied adversarial training dynamics and strategies to prevent mode collapse.
  • Transformer Architecture: Learned Transformer architecture, including self-attention mechanisms, multi-head attention, and positional encodings, crucial for LLM effectiveness.
  • Cloud Deployment: Deployed models on AWS Bedrock, exploring real-world scalability challenges.
  • Project: Delivered a fine-tuned LLM-powered AI system, demonstrating an optimized pipeline from training to deployment.
3️⃣ Module 3
⏳ ~3 months
🕒 3-hour sessions
📅 2 times per week
Deep Learning Foundations with PyTorch for Researchers

  • Machine Learning Fundamentals: Studied bias-variance tradeoff, overfitting, bagging vs. boosting, gradient descent, and regularization techniques (L1/L2).
  • Tensors & Autograd: Learned PyTorch tensors, performed matrix operations, and used automatic differentiation for gradient computation.
  • Deep Learning & Neural Networks: Implemented neural networks from scratch, explored activation functions, dropout, batch normalization, and transfer learning.
  • Computer Vision: Worked with convolutional neural networks (CNNs), pooling layers, and object detection models like YOLO and Faster R-CNN.
  • Coding & Algorithms: Practiced Python coding for ML tasks, bigram extraction, binary tree traversal, and graph algorithms.
  • Data Pipelines: Worked with DataLoaders, mini-batches, and epochs to train models efficiently.
  • Custom Model Design: Built a transformer-inspired model, introducing attention mechanisms.
  • Practical Problem-Solving: Developed machine learning solutions for fraud detection, customer churn prediction, supply chain optimization, and anomaly detection.
  • Cloud Deployment: Deployed models on AWS SageMaker
  • Project: Built an end-to-end AI pipeline with model deployment, monitoring, and optimization for real-world AI applications.
📩 Have questions?
Contact us for more details!
Phone
+1 650 961 2044
Address
830 Stewart drive, #106,
Sunnyvale, CA 94085
Email
contactus@portnov.com