“`html Daniel Alan Nelson – Prompt Engineering Portfolio

Daniel Alan Nelson

Prompt Engineer • LLM Engineer • AI Automation Developer

I design high-impact prompts and build LLM-powered systems that solve real business problems.

About Me

I specialize in prompt engineering, LLM reasoning, and intelligent automation. My work focuses on building AI systems that combine structured prompting, retrieval-augmented generation, and Python automation to deliver real-world impact. I bring a strong foundation in machine learning, deep learning, and data engineering, supported by a comprehensive 24-week AI curriculum.

Skills Snapshot

  • Prompt Engineering
  • LLM Reasoning
  • Python Automation
  • RAG Pipelines
  • AI Safety & Evaluation
  • Machine Learning Fundamentals

Projects

Personal AI Assistant with Memory

Description: A multi-turn conversational assistant with memory, tool use, and safety layers.

Skills: Prompt orchestration, system prompts, tool integration, safety prompting

Tech: Python, OpenAI API, LangChain

LLM-Powered Data Analyst

Description: Upload a CSV and receive automated insights, SQL queries, and charts.

Skills: Structured prompting, reasoning, data analysis

Tech: Python, Pandas, Streamlit

Document QA System (RAG Pipeline)

Description: Embeddings + vector search + context-aware prompting for grounded answers.

Skills: Retrieval-augmented generation, embeddings, vector databases

Tech: FAISS or Pinecone, Python, Transformers

Prompt Pattern Library

Description: A curated library of 20–30 prompt patterns with examples and use cases.

Skills: Prompt design, evaluation, documentation

Tech: Markdown, GitHub Pages (or static site generator)

Automated Workflow Engine (Python + LLM)

Description: LLM-powered automation for summarization, classification, and reporting.

Skills: Python automation, applied prompting

Tech: Python, FastAPI (or similar framework)

LLM Safety & Evaluation Suite

Description: A suite of adversarial prompts, test prompts, and evaluation metrics.

Skills: Safety prompting, evaluation, red-teaming

Tech: Python, OpenAI API

Skills

Core Prompt Engineering Skills

  • Prompt patterns (Chain-of-Thought, ReAct, RAG, self-critique)
  • LLM reasoning & structured output design
  • Safety prompting & evaluation
  • Retrieval-augmented generation (RAG)
  • Adversarial prompt testing and red-teaming

Technical Skills

  • Python
  • Pandas, NumPy
  • Scikit-Learn, PyTorch
  • FastAPI, Docker
  • Vector databases (FAISS, Pinecone, Chroma)
  • Cloud fundamentals (AWS, Azure, GCP)

Tools

  • OpenAI API
  • Azure OpenAI
  • LangChain
  • Git & GitHub

24-Week AI & Prompt Engineering Curriculum

Week 1 — Prompting Basics + Intro Python

Books

  • The Art of Prompt Engineering with ChatGPT — Nathan Hunter
  • Automate the Boring Stuff with Python — Al Sweigart (Ch. 1–3)

YouTube

  • DeepLearning.AI — ChatGPT Prompt Engineering for Developers
  • Programming with Mosh — Python Tutorial for Beginners

Week 2 — Prompt Patterns + Python Fundamentals

Books

  • The Art of Prompt Engineering (Prompt patterns section)
  • Automate the Boring Stuff (Ch. 4–6)

YouTube

  • Prompt Engineering Institute — Prompt Patterns
  • freeCodeCamp — Python for Beginners

Week 3 — Pandas + NumPy

Books

  • Python for Data Analysis — Wes McKinney (Ch. 1–5)

YouTube

  • Corey Schafer — Pandas Tutorial Series
  • freeCodeCamp — NumPy Tutorial

Week 4 — Applied Prompting + Small Python Projects

Books

  • Automate the Boring Stuff (Project chapters)

YouTube

  • Sentdex — Automating Tasks with Python
  • DeepLearning.AI — Advanced Prompting Techniques

Week 5 — Intro to Machine Learning

Books

  • Hands-On Machine Learning — Géron (Ch. 1–2)
  • The Hundred-Page Machine Learning Book (Intro chapters)

YouTube

  • Andrew Ng — Machine Learning Course (Week 1)
  • StatQuest — What is Machine Learning

Week 6 — Regression & Classification

Books

  • Hands-On ML (Ch. 3–4)
  • Intro to ML with Python — Müller & Guido (Ch. 1–2)

YouTube

  • StatQuest — Linear Regression
  • StatQuest — Logistic Regression
  • freeCodeCamp — Scikit-Learn Crash Course

Week 7 — Model Evaluation & Feature Engineering

Books

  • Hands-On ML (Ch. 5–6)

YouTube

  • StatQuest — Precision, Recall, F1
  • StatQuest — ROC & AUC
  • Krish Naik — Feature Engineering Tutorials

Week 8 — Unsupervised Learning + ML Project

Books

  • Hands-On ML (Ch. 8 — Clustering)

YouTube

  • StatQuest — K-Means Clustering
  • StatQuest — PCA
  • Corey Schafer — Project-Based ML Tutorials

Week 9 — Neural Network Fundamentals

Books

  • Deep Learning — Goodfellow (Ch. 6)
  • Neural Networks and Deep Learning — Nielsen (Ch. 1–2)

YouTube

  • 3Blue1Brown — Neural Networks Series
  • Sentdex — Neural Networks from Scratch

Week 10 — CNNs & Image Classification

Books

  • Deep Learning with Python — Chollet (CNN chapters)

YouTube

  • 3Blue1Brown — Convolutions
  • freeCodeCamp — PyTorch for Deep Learning (CNN section)

Week 11 — RNNs, LSTMs, GRUs

Books

  • Deep Learning — Goodfellow (Sequence modeling chapter)

YouTube

  • StatQuest — RNNs, LSTMs Explained
  • Sentdex — RNNs in PyTorch

Week 12 — Transformers & NLP

Books

  • Deep Learning with Python (NLP chapter)

YouTube

  • Jay Alammar — The Illustrated Transformer
  • HuggingFace — Transformers Course Playlist

Week 13 — PyTorch/TensorFlow Training Pipelines

Books

  • Deep Learning with Python (Training & tuning chapters)

YouTube

  • freeCodeCamp — PyTorch Full Course
  • freeCodeCamp — TensorFlow 2.0 Full Course

Week 14 — Deep Learning Project

Books

  • No new books

YouTube

  • Krish Naik — End-to-End DL Projects
  • Patrick Loeber — Deploying ML Models

Week 15 — SQL & Data Modeling

Books

  • Fundamentals of Data Engineering — Reis & Housley (Ch. 1–3)

YouTube

  • freeCodeCamp — SQL Full Course
  • Corey Schafer — SQL Tutorial

Week 16 — ETL/ELT Pipelines

Books

  • Fundamentals of Data Engineering (Pipeline chapters)

YouTube

  • DataTalksClub — Data Engineering Zoomcamp (ETL module)
  • Seattle Data Guy — ETL Explained

Week 17 — Spark & Big Data Tools

Books

  • Designing Data-Intensive Applications — Kleppmann (Distributed systems chapters)

YouTube

  • freeCodeCamp — Apache Spark Full Course
  • Databricks — Spark Essentials

Week 18 — Cloud Platforms & Data Warehouses

Books

  • Fundamentals of Data Engineering (Cloud chapters)

YouTube

  • Adam Marczak — Azure Data Engineering Tutorials
  • Stephane Maarek — AWS Data Engineering

Week 19 — Streaming Systems & Kafka

Books

  • Streaming Systems — Akidau

YouTube

  • Confluent — Kafka Crash Course
  • DataTalksClub — Streaming Module

Week 20 — Capstone Planning

Books

  • Machine Learning Design Patterns — Lakshmanan (Planning chapters)

YouTube

  • Google Cloud — MLOps Crash Course

Weeks 21–22 — Capstone Development

Books

  • Building Machine Learning Pipelines — Hapke

YouTube

  • Krish Naik — End-to-End ML Pipeline
  • TechWorld with Nana — Docker for Beginners

Week 23 — Capstone Refinement

Books

  • No new books

YouTube

  • FastAPI — API Deployment Tutorials
  • Patrick Loeber — Deploy ML Models to Cloud

Week 24 — Final Review & Portfolio Prep

Books

  • No new books

YouTube

  • Ken Jee — How to Build a Data Science Portfolio
  • Alex The Analyst — Portfolio Projects

Resume

You can mirror the strong resume we built here. For now, this section can include:

Professional Summary

Driven AI practitioner specializing in prompt engineering, LLM reasoning, and intelligent automation. Skilled at designing high-impact prompts, building LLM-powered systems, and integrating AI into real-world workflows. Strong foundation in Python, machine learning, deep learning, and data engineering, backed by a structured 24-week AI curriculum.

Core Skills

  • Prompt Engineering & LLM Reasoning
  • Prompt Patterns (CoT, ReAct, RAG, Self-critique, Few-shot)
  • Python Automation & Scripting
  • Retrieval-Augmented Generation (RAG)
  • LLM Evaluation, Safety & Guardrails
  • API Integration (OpenAI, Azure, Anthropic)
  • Embeddings & Vector Databases
  • Machine Learning Fundamentals
  • Deployment (FastAPI, Docker)

Training & Curriculum

Comprehensive 24-week AI Learning Curriculum covering: Prompt Engineering, Python, Machine Learning, Deep Learning, Data Engineering, and MLOps & Deployment.

Contact

If you’d like to connect about opportunities, collaborations, or projects, feel free to reach out.

“`