AI for Technology Professionals

Engineer, fine-tune and ship production-ready AI use cases — end-to-end, in just two days.

Quick Facts


Duration	2 full days (08:30-17:00 each)
Format	Advanced, code-intensive workshop with live labs, pair programming & architecture clinics
Level	Advanced—assumes solid Python + Git skills and completion of AI Empowered Knowledge Worker (or equivalent)
Ideal for	• Software & ML engineers • Solution architects • Data engineers • DevOps / MLOps specialists • Technical product owners
Certification	Certificate of Applied Competency
Seats	Capped at 30 for deep-dive mentoring

Course Overview

AI for Technology Professionals is a two-day advanced workshop that takes you from “prompts in a notebook” to containerised, monitored, and governed AI services. You’ll architect retrieval-augmented generation (RAG) pipelines, fine-tune open-source LLMs, implement guardrails, and deploy resilient microservices on Kubernetes—all with reproducible DevOps practices. Leave with a deploy-ready capstone you can plug into your own stack the very next sprint.

Who Should Attend

Backend or full-stack engineers adding GenAI capabilities to products
Data & ML engineers tasked with scaling prototypes into production
Solution architects defining AI reference architectures and guardrails
DevOps / platform teams responsible for CI/CD, observability & cost control
Technical product owners overseeing enterprise AI roadmaps

Prerequisites

Comfortable with:

Python 3.10+, virtual environments & CLI
Git workflows (branching, PRs)
Basic Docker commands
A laptop (16 GB RAM recommended) with Docker Desktop and VS Code pre-installed. All other tooling is provided in cloud sandboxes.

Learning Objectives

By the end of the workshop you will:

Design production-grade GenAI architectures using RAG, agents & service meshes.
Build vector search pipelines with FAISS / Qdrant and embed documents at scale.
Fine-tune open-source models (e.g., Llama-3) via LoRA & evaluate with open benchmarks.
Containerise & Deploy AI microservices to Kubernetes with automated CI/CD.
Implement runtime guardrails, observability & cost-aware autoscaling.
Govern models with policy frameworks covering bias, privacy & licensing.

Curriculum Highlights

Day	Time	Module	Key Take-Aways
1	08:30	Landscape & Architecture Patterns	3 reference patterns: SaaS API, private RAG, on-prem fine-tune
	09:45	Vector DB & Embeddings Lab	FAISS vs Pinecone vs Qdrant; chunking, metadata, hybrid search
	11:30	Advanced Prompt & Tooling Chains	LangChain VSCode debug; function calling; agent tooling
	12:30	Lunch	—
	13:15	RAG Service Build	Hands-on: ingest → embed → query → answer with citations
	15:45	Guardrails & Safety	Prompt injection tests, output filters, policy enforcement
	17:00	Reflection & Git Push	Code review, PR hygiene

2	08:30	Model Fine-Tuning & Evaluation	LoRA on 8-bit GPUs/CPUs, eval with HELM & MT-Bench
	11:00	Containerisation & CI/CD	Dockerfile best practices, GitHub Actions, image scanning
	12:30	Lunch	—
	13:15	Kubernetes & Service Mesh	Helm, KEDA autoscaling, Istio traffic shifts
	15:00	Observability & Cost Controls	Prometheus, Grafana, OpenTelemetry traces, per-token cost dashboards
	16:00	Capstone Sprint & Demo	Teams deploy a live RAG microservice with monitoring
	16:45	Certification & Next Steps	Digital badge, alumni channels, advanced reading list

Key Benefits & Transferable Skills

Deploy-ready GenAI microservice template (repo handed over)
Reusable Helm charts, CI/CD pipelines & IaC snippets
Practical experience fine-tuning and evaluating open models
Governance checklist aligning with POPIA/GDPR & OSS licences
Digital badge validating production AI engineering expertise

Pricing & Packages

Standard seat: ZAR 14 995
Early-bird (book ≥30 days out): ZAR 13 995
Team bundle (4+): 10 % discount + private post-course architecture clinic
Fee includes: Cloud GPU credits, datasets, meals, 6-month sandbox & Wi-Fi

FAQs

Is coding mandatory?
Yes—most labs are Python-based. Templates are provided, but you’ll edit code.

Do I need my own cloud account?
No. Temporary GPU and Kubernetes clusters are provisioned for you; we’ll show how to replicate on AWS/Azure/GCP.

How does this differ from the boot camp?
This workshop dives into code, infrastructure, and governance. You leave with a deployable service, not just workflows.

Corporate / Private Cohorts

Accelerate enterprise AI initiatives with a dedicated, NDA-compliant delivery—onsite or virtual. Contact [email protected] for custom scoping.

Post-Course Resources

180-day Git repo access & cloud sandbox
Monthly engineering office-hours with course mentors
Invitation to MindSpring TechPro Slack & quarterly hackathons

Ready to Ship Production AI?

Class size is limited to 18. Reserve your AI for Technology Professionals seat now.

Bookings covered by our flexible training-credit policy. Full terms & privacy appear in the footer.