The GenAI Engineering for Software Engineers programme is designed for software engineers who already understand code, APIs, testing, and delivery, and now need to pivot into GenAI with the right engineering mindset. Rather than positioning GenAI as a generic awareness topic, this programme helps software engineers understand how LLMs, RAG, agentic systems, and AI-enabled developer workflows can be built with the same rigour expected from modern software products.
The curriculum follows a build-forward storyline progressing from LLM foundations through AI-enabled SDLC practices, evaluation, and agent orchestration. A key differentiator is that it treats software engineers as future GenAI builders, not just tool users. Each module ends with a mini-capstone whose output becomes the starting artefact for the next module — learners progressively evolve one solution across the programme.
WHO SHOULD ATTEND
- Software engineers, application developers, backend engineers, full-stack engineers
- QA automation engineers pivoting to AI-enabled test practices
- Platform engineers and solution architects moving into GenAI delivery
- Engineering leads who need to design and govern GenAI systems in their teams
PRE-QUISITES
- Hands-on software engineering experience in at least one language — Python, Java, JavaScript, or
similar - Comfort with core engineering practices — APIs, Git, unit testing, logging, and basic CI/CD concepts
- Prior GenAI experience is not mandatory — the programme is for engineers pivoting into GenAI
- Familiarity with software architecture concepts — modular design, service boundaries, integration
patterns - Teams should ideally bring one internal engineering workflow use case to anchor the capstones
KEY OUTCOMES
- Explain the role, strengths, limitations, and engineering implications of LLMs, embeddings, retrieval, and agentic patterns from a software delivery perspective
- Design and build production-aware RAG architectures using chunking, retrieval, evaluation, and vector database patterns
- Apply GenAI across the SDLC for developer productivity, debugging, testing, documentation, and controlled workflow automation
- Use TDD, BDD, and SDD approaches to structure GenAI solution development with clear requirements and validation criteria
- Build agentic workflows using LangChain, LangGraph, MCP-compatible patterns, and observability tooling
- Incorporate governance requirements covering permissions, data sensitivity, auditability, human
review, and operational guardrails - Deliver a final production-grade capstone demonstrating architecture quality, testing, observability, and deployment readiness
