AI Solutions Developer- UCI 3097

This 13-week course is designed to equip learners to build end-to-end AI applications—operating model endpoints, designing effective prompt strategies, implementing Retrieval-Augmented Generation (RAG), adding tool-using agents, integrating OCR-driven multimodality with a lightweight UI, and applying evaluation, testing, and documentation for production-minded delivery. This intermediate course is designed for individuals with prior software engineering training who are ready to use their skills in AI application development. Through an array of interactive labs, clear, focused mini-lectures, and collaborative build projects, individuals will stand up model runtimes, orchestrate conversations, ground answers in their own data, implement reliable tool-calling workflows, ship a demo UI, and assemble a portfolio-ready capstone.  Upon successful course completion, learners will be equipped to pursue roles such as AI Solutions Developer or Full-Stack Engineer.

Qualifications & Technical Preparation To be considered for the AI Solutions Developer course, applicants must meet the minimum qualifications for a Per Scholas course, typically demonstrated through prior technical education or status as a Per Scholas Alumnus.

Foundational Competencies Success in this advanced curriculum relies on a strong grasp of Python Essentials and Object-Oriented Programming (OOP) Fundamentals. While we no longer require specific course certificates for admission, we are committed to ensuring every learner possesses these core competencies before the start date.

Self-Study Resources To support your preparation, Per Scholas provides access to a curated list of cost-free self-study materials. You are also welcome to leverage any alternative resources or platforms of your choosing to attain these skills. Mastering these fundamentals will ensure you are best positioned to engage with the AI integration and solution-building concepts covered in this course.

Course Goals

Upon successful completion of all course requirements, learners will 

• Design end-to-end AI application architectures that compose prompting, RAG, agentic workflows, and multimodality.
• Implement model-orchestration flows with function/tool calling, memory, validation, and basic guardrails.
• Build retrieval pipelines (ingest, chunk, embed, index, retrieve) that ground answers with citations.
• Develop user-facing demos (CLI/API/UI) and package code with tests, configs, and reproducible environments.
• Evaluate performance, reliability, and cost, using logs, metrics, documentation, and stakeholder-ready presentations to report results.