Applied AI Engineering
Master the skills to build and deploy production-grade AI applications in this 14-week hands-on Applied AI Engineering program.
June 2026 Intake in Progress
Part-time Remote
Start Date:
June 29th, 2026
Course Duration:
14 Weeks
Mode of Learning:
100% Online Classes | Mondays, Tuesdays, Thursdays (6 pm to 9 pm E.A.T) | 6 Hours Weekly Independent Lab & Project Work.
Tuition Fee:
Ksh 150,000 (includes $125 NVIDIA Exam fee)
Architect, Deploy, and Scale Production-Ready AI
Many learning paths focus on theoretical knowledge or isolated tools. While these provide a strong foundation, they often leave a gap between building a simple demo and shipping a reliable product. Applied AI Engineering is a production-first program that bridges the gap between AI prototypes and enterprise-grade systems.
You’ll master the complexities of LLM-powered applications and agentic workflows using frameworks like LangChain and LlamaIndex. The program provides hands-on experience with FastAPI, Docker, and CI/CD pipelines while preparing you for the global NVIDIA-Certified Associate (NCA-GENL) exam.
By the end of this course, you’ll develop a professional portfolio of AI systems grounded in real-world Kenyan use cases, such as financial inclusion and agricultural advisory.
Course Details
It is the discipline of building, integrating, and maintaining AI systems within a production environment. It focuses on the end to end lifecycle: from retrieval-augmented generation (RAG) and fine-tuning to deployment, cost optimization, and security.
This course is designed for working software engineers and data scientists with 2–5 years of experience who want to transition into AI engineering roles.
This course is not intended for:
- Absolute beginners with no coding or Python experience.
- Senior AI researchers seeking deep theoretical or academic knowledge.
- Learners whose primary goal is certification-only training without practical application.
- Intermediate Python skills (functions, classes, APIs, basic testing, and debugging).
- Basic understanding of APIs and cloud platforms
- 55% or higher score on a 15-question quiz covering Python, software engineering foundations, Git/version control, ML basics, and APIs.
Moringa provides a specialised, career-accelerating environment where you master the complex architectures required to deploy AI at scale.
- Join an established community of experienced software engineers and data scientists.
- Access high-level technical upskilling through 100% online evening sessions designed to fit your work schedule.
- Master the full AI lifecycle using Docker, CI/CD, and LLMOps to deploy scalable, production-ready systems.
- Architect autonomous agentic workflows and multi-agent coordination patterns using LangChain and LlamaIndex.
- Earn global credibility with structured preparation for the NVIDIA-Certified Associate (NCA-GENL) exam.
- Build a high-impact portfolio grounded in real-world Kenyan use cases and local data compliance.
Move beyond prompting with AI and start building with it at production scale, with real systems, real use cases, and an industry-recognized credential.
Get Started - Apply NowCurriculum Overview
Apply AI engineering concepts and work with LLMs to solve real-world problems.
- Week 1: Introduction to AI Engineering and LLMs– AI Engineering vs. Data Science, Model Trade-offs (Open-source vs. Proprietary), Prompt Engineering, Python integration, Kenyan Use Cases (Healthcare/Finance).
- Week 2: AI Frameworks and Tools – LangChain & LlamaIndex, Agent Architecture (Planning/Reasoning), Tool Calling, Multi-agent Patterns, MCP (Model Context Protocol), Git Workflows.
- Week 3: Model Evaluation, Monitoring, and Observability – Metrics (BLEU/ROUGE/F1), Monitoring Data/Model Drift, Cost Observability (TCO/Token tracking), Prometheus, Grafana, Evidently AI.
Build production MCP servers to turn enterprise data into actionable protocol primitives for agentic AI systems.
- Week 4: Fine-Tuning LLMs – Dataset curation, Hugging Face Trainer, Nebius AI Studio, PyTorch, LLaMA/Mistral Fine-tuning, Transfer Learning, Agricultural Advisory Case Study.
- Week 5: Multimodal AI Systems – Multimodal Models (CLIP/DALL·E/Whisper), Image Captioning, Audio-to-Text, Cross-modal Retrieval, Gradio Interfaces.
- Week 6: API Integration, Microservices, and MCP Servers – Secure backends with FastAPI & Docker, MCP SDK (Servers/Clients), Kubernetes, State & Memory Management, Version Control for AI.
- Week 7: Break Week
Implement LLMOps for continuous deployment and security while ensuring performance and cost efficiency.
- Week 8: Deploying LLMs-Based Applications at Scale – Performance and Cost Optimisation – Model Quantisation & Pruning, Serverless Architecture (Azure/AWS), Cost Modelling (TCO), Caching, Batching, Autoscaling.
- Week 9: LLMOps and Continuous Integration – CI/CD Pipelines (GitHub Actions/Azure DevOps), Prompt & Config Versioning, Automated Regression Testing, A/B Testing, MLflow.
- Week 10: AI Security and Compliance – Model Poisoning, Adversarial Attacks, Kenya Data Protection Act, GDPR for AI, Key Management (KMS/Vault).
- Week 11: Break Week
Design, develop, and deploy a comprehensive, production-grade AI solution for a real organisational problem.
- Week 12: Advanced Multimodal AI – Vision-Language Models, Audio-Text Integration, Stable Diffusion, Multimodal Bias, Kenyan Retail Analytics.
- Week 13: Capstone Development, Finalisation, and Testing – Scalable & Secure Implementation, Agile Sprint Planning, Functionality & Performance Testing, Technical Documentation.
- Week 14: Capstone Presentation & Certification Prep – Industry Pitch & Q&A, NVIDIA (NCA-GENL) Blueprint Review, Timed Practice Exams, Certification Sitting.
Design and deploy a production-ready AI solution addressing real-world challenges in healthcare, logistics, or retail. Projects are grounded in real Kenyan organizational use cases and may be industry-sponsored to meet professional workplace expectations.
Get structured preparation for your NVIDIA-Certified Associate credential through hands-on labs grounded in real Kenyan organisational use cases.
Career Opportunities in AI Engineering
- AI Engineer
- Generative AI Specialist
- AI Integration Specialist
- MLOps Engineer
- AI Platform Engineer
- AI Solutions Architect
- RAG / Data Engineer (AI-Focused)
Designs and builds the core logic of AI-powered applications. They focus on model selection, API integration, and ensuring the brain of the app functions correctly within the product environment.
Specializes in the nuances of Large Language Models. They focus on advanced prompting, fine-tuning, and optimizing GenAI outputs to ensure high accuracy and brand-safe interactions.
The bridge between AI and legacy systems. They ensure new AI capabilities connect seamlessly with existing databases and enterprise software without disrupting established workflows.
Manages the infrastructure and plumbing of AI. They build the CI/CD pipelines and monitoring tools required to keep models running reliably and scaling efficiently in a live environment.
Builds the internal tools and environments that allow other developers to deploy AI. They focus on creating a scalable paved path for AI development across an entire organization.
Translates complex business problems into technical AI blueprints. They decide which models, cloud providers, and data structures provide the best ROI for a specific company use case.
Specializes in the retrieval aspect of AI. They build high-performance vector databases and data pipelines that allow an AI to read and process a company’s private data accurately.
Designs and builds the core logic of AI-powered applications. They focus on model selection, API integration, and ensuring the brain of the app functions correctly within the product environment.
Specializes in the nuances of Large Language Models. They focus on advanced prompting, fine-tuning, and optimizing GenAI outputs to ensure high accuracy and brand-safe interactions.
The bridge between AI and legacy systems. They ensure new AI capabilities connect seamlessly with existing databases and enterprise software without disrupting established workflows.
Manages the infrastructure and plumbing of AI. They build the CI/CD pipelines and monitoring tools required to keep models running reliably and scaling efficiently in a live environment.
Builds the internal tools and environments that allow other developers to deploy AI. They focus on creating a scalable paved path for AI development across an entire organization.
Translates complex business problems into technical AI blueprints. They decide which models, cloud providers, and data structures provide the best ROI for a specific company use case.
Specializes in the retrieval aspect of AI. They build high-performance vector databases and data pipelines that allow an AI to read and process a company’s private data accurately.
Get Started
