REGISTRATION FOR BATCH 7 IS NOW OPEN! 1 January 2027 — see fees and dates

ProgrammesDiplomaAI Engineering

Diploma

AI Engineering

Build deep, practical expertise in AI engineering, develop the confidence to solve real-world problems, and prepare for the opportunities shaping the future of technology.

1 yearDuration
On CampusFormat
FlexiblePacing
English & UrduLanguage
48Weeks
192Sessions
4Milestone Projects
4Oral Defenses
The Roadmap

What You’ll Learn

A carefully sequenced journey from core engineering foundations to building, deploying, and scaling real AI systems.

What You’ll Learn

Before Month 1 begins, every student proves they can already build — enough Python and software engineering practice to make the rest of the year possible. Only students who pass move into Month 1.

Outline

Week P1 — Python FundamentalsWeek P2 — Working Like an EngineerWeek P3 — APIs & Real Code

Outcomes

Gate Assessment (pass/fail) — build and submit a CLI tool that calls a public API, handles real error cases, is tracked in Git, and includes passing tests. Reviewed by instructor, no partial credit.

Most courses jump straight to "build a chatbot." Here, students understand sampling and context mechanics before they ever touch a framework — so when something breaks in Month 2, they know why.

What You’ll Learn

Tokens, context windows, and sampling parameters; working with Claude and OpenAI-compatible APIs; prompt engineering patterns; and context engineering — the differentiator that explains why RAG works the way it does.

Outline

Week 1 — Orientation & Core LLM MechanicsWeek 2 — Working with Model APIsWeek 3 — Prompt EngineeringWeek 4 — Context Engineering

Outcomes

Milestone 1: a structured-output tool — system prompt, function calling, validated output — defended in a live design walkthrough.

What You’ll Learn

Embeddings and semantic search; indexing and querying a real vector database; building a RAG pipeline from raw chunking through to a framework-based rebuild with LangChain and LlamaIndex.

Outline

Week 5 — EmbeddingsWeek 6 — Vector DatabasesWeek 7 — Building RAG from ScratchWeek 8 — RAG Frameworks & Milestone 2

Outcomes

Milestone 2: a RAG system built over a real Pakistani-context dataset — must explain retrieval failures, not just demo success.

What You’ll Learn

Building AI agents by hand before reaching for an SDK; the Model Context Protocol end to end; evaluation and observability; and the safety practices every production system needs.

Outline

Week 9 — AI AgentsWeek 10 — Model Context Protocol (MCP)Week 11 — Evaluation & ObservabilityWeek 12 — AI Safety, Ethics & Capstone

Outcomes

Oral Defense 1: present and defend a live RAG or agent-based system — why this chunking strategy, why this eval approach, what breaks under adversarial input.

Quarter Outcome

A working system a student built, shipped, and can defend under questioning — not a tutorial they followed.

Entry requires a passed Q1 capstone. Q1 asks "does it work?" Q2 asks "does it work at 2am when traffic spikes, when a user tries to break it, and when the bill triples?"

What You’ll Learn

Wrapping AI logic in a real FastAPI service; containerizing and deploying it publicly; adding Postgres and Redis-backed state; and automating the whole pipeline with CI/CD.

Outline

Week 13 — Serving AI SystemsWeek 14 — Containerization & DeploymentWeek 15 — Databases & State for AI AppsWeek 16 — CI/CD & Infrastructure as Code

Outcomes

Milestone 4: a previous project deployed as a live, authenticated, publicly accessible API — instructor live-tests the endpoint and tries to break it.

What You’ll Learn

Multi-agent orchestration with LangGraph, CrewAI, and AutoGen; long-term agent memory; guardrails and fallback strategies; and hybrid + reranked retrieval for real accuracy gains.

Outline

Week 17 — Multi-Agent Orchestration FrameworksWeek 18 — Agent Memory SystemsWeek 19 — Guardrails, Reliability & Fine-Tuning AwarenessWeek 20 — Advanced Retrieval

Outcomes

Milestone 5: a production-grade multi-agent system with memory and guardrails — instructor triggers a live tool failure and it must degrade gracefully.

What You’ll Learn

Caching and model-routing strategies that actually move a monthly AI bill; dashboards and SLOs; production security hardening; and defending a fully deployed, load-tested system.

Outline

Week 21 — Performance & Cost OptimizationWeek 22 — Monitoring & Observability at ScaleWeek 23 — Security HardeningWeek 24 — Capstone 2 Build & Oral Defense

Outcomes

Oral Defense 2: defend what breaks the system, what it costs to run at scale, and what changes at 10x users.

Quarter Outcome

A student who can take a working AI prototype and turn it into something a company would actually deploy — the gap between a portfolio demo and a system a company trusts in production.

Entry requires passed Q1 and Q2 capstones. Real AI Engineer roles fork this way in practice — a platform hire, a product hire, and a research-leaning hire do genuinely different daily work under the same job title.

What You’ll Learn

Kubernetes for AI workloads, model serving at scale with vLLM/TGI, unified LLM gateways, and building internal developer platforms other teams plug into.

Outcomes

Comfortable orchestrating AI workloads and routing traffic across multiple model providers.

What You’ll Learn

Multi-region deployment and failover, GPU resource and cost governance, building observability platforms from scratch, and chaos engineering.

What You’ll Learn

Build and defend a full internal AI platform — self-serve access, usage tracking, per-team budgets — as if presenting to a Head of Engineering.

Outcomes

Capstone Defense: job-ready for AI Platform Engineer or Infrastructure Engineer roles — the person other engineers depend on to keep AI systems running.

Quarter Outcome — All Lanes

A shared AI Engineer foundation plus a specialized edge that maps to how hiring managers actually differentiate candidates — not just "knows AI," but "is the platform person / the product person / the research-leaning person" on a team.

Not new technical content — this is where everything from Q1–Q3 gets pointed at the outside world: real clients, a real portfolio, real interviews, a real income path.

What You’ll Learn

Working like a real dev team — sprint planning, code review culture — then live, paired work on an actual client engagement with real deadlines and real stakeholder feedback.

Outcomes

Deliverable — a real client testimonial or reference, from presenting deliverables directly to the client, not the instructor.

What You’ll Learn

Turning four capstones into a polished portfolio site with real case studies; live system-design and debugging interview practice; behavioral interviewing; and rate-setting for local and international clients.

Outcomes

Deliverable — a live portfolio site, plus one submitted freelance proposal or job application.

What You’ll Learn

The launch month: a final capstone combining the student's lane specialization with the full skill stack, built and presented as if pitching a real employer — then a public showcase with an external industry panel.

Outcomes

Final Defense — graduation, certification, and a concrete next step: join Special Technician, freelance, placement with a partner company, or move to a deeper ML Engineer track.

Quarter Outcome

A graduate with a real client reference, a real portfolio, interview and negotiation readiness, and a concrete next step — not a certificate and a "good luck."

Step-by-Step Path

Follow a proven sequence designed for real results.

Build Real Projects

Apply your skills with hands-on projects every quarter.

Expert Guidance

Learn from industry experts and community support.

Career-Ready

Graduate with production experience and confidence.

AI-Lab System

Powered by our own classroom technology

Every class runs through Aisha Cahn College’s own AI-Lab platform — attendance, assignments, and grading, all automatic.

ai-lab.system — capability statusLive

Schedule

Monday – Saturday · 8:30 AM – 2:00 PM

Assessment

1 Quiz per Week1 Assignment per WeekCompulsory Capstone Project

Capabilities

8 automated
tap to expand

Meet Your Instructor

Learn from the Experts

Learn from people who do the work, not just teach it. Gain practical insights, real-world guidance, and knowledge shaped by industry experience.

Mr. Muhammad Musa Kaleem

AI Instructor · Senior Backend & MLOps Engineer

Experience

  • Founding Engineer, AI-Lab System

    Aisha Cahn Foundation · 2025

  • Computer Vision Engineer

    Leia Robots · Jan 2026 – Present

  • Senior Backend Developer

    Gigmasters, Lahore · Feb 2024 – Jun 2025

  • Machine Learning Engineer

    Wind to Energy, Rostock · Apr 2019 – Dec 2023

Education

  • MSCS

    University of Rostock · 2019 – 2023

  • BSCS

    University of Engineering & Technology (UET), Peshawar · 2012 – 2016

Social Links

Student Work

Built by Our Students

Ready to start?

Apply for AI Engineering

Admissions open

New batch begins 1 January.

Seats in each batch are limited. Message us and we will reply the same working day — or come and see the campus first.

0Days
00Hours
00Minutes
  • CampusMuslim Hands Educational Complex, Wazirabad, Punjab
  • Office hoursMonday to Saturday, 9:00 AM – 4:00 PM
  • WhatsApp+92 300 1453445
Wazirabad, PunjabAisha Cahn CollegeRated 5.0 ★ on GoogleDirections →