AI & Machine Learning Developer

A 10-week applied program focused on the data and engineering skills needed to build generative AI systems — data pipelines, RAG, function calling, lightweight fine-tuning, AI agents, and end-to-end evaluation.

Program Goals

• Build the technical foundation needed for AI engineering and data engineering roles
• Prepare students to work with data pipelines that support LLMs and generative AI systems
• Develop applied experience with modern AI tools, model workflows, and evaluation practices
• Create a structured career pipeline for high-demand roles in AI systems

Learning Outcomes

• Explain fundamentals of LLMs and the role of data in AI scaling
• Collect, extract, clean, label, and prepare data for generative AI
• Implement scalable data processing methods
• Use synthetic data and human data workflows
• Work with text, image, audio, and video pipelines
• Build retrieval-augmented generation (RAG) systems
• Apply function calling, orchestration, and evaluation methods
• Complete lightweight fine-tuning and summarization workflows
• Design and present an end-to-end capstone AI system

10-Week Course Schedule

• Week 1 — Foundations and Tooling: Generative AI landscape, LLM fundamentals, dev environments, data’s role in AI scaling.
• Week 2 — Agent Workflows: AI agents, task decomposition, tool use, prompt patterns, human data workflows.
• Week 3 — OCR, ASR, and TTS: Multimodal data extraction, OCR, speech-to-text, text-to-speech.
• Week 4 — RAG Foundations: Retrieval-augmented generation, embeddings, vector databases, chunking strategies.
• Week 5 — Hybrid Search & Data Quality: Keyword search, semantic search, hybrid retrieval, filtering, visualization.
• Week 6 — Function Calling: Structured outputs, tool/function calling, schema design, reliability patterns.
• Week 7 — Orchestration & Evals: Workflow orchestration, evaluation design, model comparison, human-in-the-loop review.
• Week 8 — Fine-Tuning & Summarization: Lightweight fine-tuning, synthetic data generation, summarization pipelines.
• Week 9 — Scaling AI Workflows: Data pipelines, databases, monitoring, cost/performance tradeoffs.
• Week 10 — Capstone: End-to-end AI system design, integration, presentation, reflection.

Capstone Project

The capstone is an end-to-end AI system that integrates the major skills from the course. Each project includes a defined user problem, a data collection or extraction process, data cleaning/filtering/annotation, a model workflow (RAG, function calling, fine-tuning, or summarization), a clear evaluation plan, and a final presentation or demonstration.

Recommended Tools & Technologies

Python and common data libraries; APIs for large language models and generative AI systems; data storage and database tools; embedding and vector search tools; annotation and evaluation workflows; and development tools for reproducible projects.

Weekly Format

Total commitment: 13.5 hours per week. Live lecture (2 hrs), hands-on programming lecture (1.5 hrs), office hours (1.5–2 hrs), weekly homework (~5 hrs), independent project work (~3.5–5.5 hrs).

Who Should Enroll

• Senior undergraduate students preparing for applied AI engineering roles
• Technicians and engineers supporting AI-enabled operations
• Employers building internal AI capability