All Tracks

AI Engineer

Design, build, evaluate, and operate production AI systems

An engineering path from measurable problem framing and data contracts through classical and deep learning, LLM applications, agents, evaluation, security, and production operations. The work centers on reviewable implementations, test evidence, and explicit operating limits.

8000 planned XP~57 hoursFoundations–Advanced

Prerequisites

  • No prior machine-learning study is required; complete AI Engineering Foundations before Classical Machine Learning
  • Working Python knowledge: functions, classes, packages, virtual environments, testing, and debugging
  • Command-line and Git proficiency, plus working knowledge of HTTP and JSON
  • Working familiarity with pandas or another tabular-data stack, practical SQL, web APIs, and asynchronous Python; complete the course-provided bridge before the second lab for any missing area
  • Foundational algebra, probability, statistics, and linear algebra; the track applies these foundations rather than replacing a mathematics course
Lab 1800 planned XP

AI Engineering Foundations

Start with plain-language AI concepts, then translate an ambiguous public-service problem into a measurable ML task, establish a baseline, and build a leakage-safe data workflow.

You will learn:
  • Produce an Arabic-English vocabulary guide that distinguishes AI, machine learning, deep learning, and generative AI with one decision example and one limit for each
  • Write a problem brief that names the decision, owner, prediction target and timing, available data, baseline, and measurable success criteria
  • Validate the dataset against a documented contract and run a baseline whose features and split exclude target and future-data leakage
You'll build:AI vocabulary guide, problem brief, validated dataset, and leakage-safe baseline

Lab assessment

80% pass threshold

Complete the four-part artifact for one bounded prediction decision. Use a reviewable dataset, record every validation check, and keep the final test partition untouched.

Submission

Submit the bilingual vocabulary guide, problem brief, data contract and validation report, runnable baseline, and a short README with reproduction steps.

Assessment rubric
Decision and target framing20%

The brief defines the unit, prediction time, target, action, owner, baseline, and measurable release criteria without substituting a model score for the service outcome.

Data contract and validation evidence25%

Schema, types, ranges, missingness, provenance, label timing, and failed checks are documented with reproducible evidence.

Baseline correctness25%

The baseline runs from a clean environment, fits only on training data, uses a decision-relevant metric, and reports deterministic results.

Leakage and limitation controls20%

Feature availability and split logic are justified, at least two leakage paths are tested, and data or deployment limitations are explicit.

Bilingual vocabulary precision10%

Arabic and English terms are accurate, paired consistently, and understandable to a reviewer without machine-learning experience.

Lab 21350 planned XP

Classical Machine Learning

Learn what classical ML means in everyday terms, then build strong tabular models with the right features, objectives, thresholds, and error analysis before reaching for deep learning.

You will learn:
  • Produce a plain-language comparison that selects classification for the stated decision and rules out regression, clustering, and anomaly detection with evidence
  • Implement a versioned scikit-learn pipeline that fits preprocessing and features inside leakage-safe training and validation folds
  • Select an operating threshold and publish an error report covering calibration, confusion costs, important slices, and actionable failure patterns
You'll build:Plain-language ML comparison, reproducible classification pipeline, and error report

Lab assessment

80% pass threshold

Train and compare a defensible classifier against the established baseline. Freeze the test set until model, preprocessing, metric, and threshold choices are complete.

Submission

Submit the method comparison, source and environment lockfile, runnable pipeline, experiment table, threshold analysis, and error report.

Assessment rubric
Method selection20%

The selected task, objective, baseline, and model family follow from the decision and data, and rejected alternatives have technically sound reasons.

Pipeline correctness and reproducibility30%

Preprocessing, encoding, feature generation, fitting, and inference are one reproducible pipeline with fixed seeds and no fit-time access to validation or test data.

Threshold and error evidence25%

The report compares the baseline and candidate on appropriate metrics, justifies the threshold from error costs, and inspects calibration and meaningful slices.

Leakage, imbalance, and limits15%

The work tests leakage and imbalance risks, avoids unsupported causal claims, and identifies conditions under which the classifier must not be used.

Plain-language decision summary10%

The comparison and error findings are concise, traceable to results, and understandable to a non-technical decision owner.

Lab 31000 planned XP

Deep Learning

Understand tensors, automatic differentiation, training loops, regularization, embeddings, and the transformer architecture.

You will learn:
  • Implement and test a PyTorch model whose tensor shapes, dtypes, outputs, loss, and target contract are explicit
  • Run a reproducible training experiment that records configuration, seed, learning curves, validation metrics, and the selected checkpoint
  • Diagnose underfitting, overfitting, or unstable gradients from evidence and justify whether the trained model improves on a simpler alternative
You'll build:Trained PyTorch model with a documented experiment

Lab assessment

80% pass threshold

Train one compact model on the supplied task, beginning with shape assertions and a tiny-batch overfit check. Compare it with the simplest credible baseline.

Submission

Submit model and training code, pinned environment, configuration, checkpoints or hashes, learning curves, metric table, and experiment note.

Assessment rubric
Tensor and model contract20%

Automated checks cover input, intermediate and output shapes, dtypes, label encoding, loss compatibility, and inference mode.

Training implementation30%

The loop handles batches, optimizer steps, gradient reset, validation, checkpoint selection, and device placement correctly.

Experiment evidence25%

Configuration and seeds reproduce the reported curves and metrics, and the selected checkpoint is supported by held-out validation evidence.

Failure diagnosis and controls15%

The note identifies observed failure signals, applies proportionate regularization or debugging, and records data, compute, and misuse limits.

Model-choice justification10%

The conclusion states whether deep learning is warranted relative to the baseline, using quality and operational evidence rather than architecture popularity.

Lab 4900 planned XP

MLOps and Model Serving

Make training reproducible, package models behind typed interfaces, and operate them with monitoring, safe releases, and rollback plans.

You will learn:
  • Package a versioned model and preprocessing pipeline behind a typed inference contract with validated requests and traceable responses
  • Demonstrate repeatable build, startup, health, readiness, prediction, and overload tests from a clean environment
  • Define service, data, and model monitors with owners, alert thresholds, release gates, and a tested rollback procedure
You'll build:Reproducible model service with monitoring and rollback

Lab assessment

80% pass threshold

Serve the previous model as an immutable versioned artifact. Exercise normal, invalid, concurrent, dependency-failure, and rollback paths and retain the resulting evidence.

Submission

Submit the service repository, build manifest, API contract, automated test output, monitoring specification, release checklist, and rollback record.

Assessment rubric
Artifact reproducibility20%

A clean build produces a named model, preprocessing, dependency, configuration, and schema version whose provenance and hash are recorded.

Inference contract and correctness25%

The interface rejects invalid inputs, preserves training-time feature semantics, returns model metadata, and passes golden prediction tests.

Reliability test evidence20%

Readiness, timeout, concurrency, payload, dependency-failure, and overload behavior are tested against explicit service objectives.

Monitoring design20%

Metrics distinguish service health, input drift, output behavior, and delayed outcomes, with thresholds, owners, and response actions.

Release safety and rollback15%

The release gate names approval and stop criteria, protects sensitive telemetry, and includes evidence that the previous version can be restored.

Lab 5900 planned XP

LLM Application Foundations

Work with language models as probabilistic APIs: manage context, request structured outputs, and design for latency, cost, and failure.

You will learn:
  • Implement an inspectable LLM request and typed response boundary that validates structured output before application use
  • Enforce explicit context, output-token, latency, cost, retry, and concurrency budgets and report their measured behavior
  • Test malformed output, refusal, timeout, rate limit, provider error, and exhausted-budget paths with deterministic application fallbacks
You'll build:Typed LLM service with bounded retries and token budgets

Lab assessment

80% pass threshold

Build one bounded native-SDK operation that turns validated input into a typed result. Capture sanitized request metadata and exercise each defined failure path.

Submission

Submit runnable service code, schemas, configuration, focused tests, sanitized traces, budget measurements, and a failure-behavior note.

Assessment rubric
Typed request and output contract25%

Input and output schemas reject unknown or invalid values, and no generated structure reaches business logic before parsing and validation.

SDK integration correctness25%

The complete model request is explicit and testable, including messages, tools, tool choice, response format, model configuration, and structured-output settings.

Budget evidence20%

Measured tests demonstrate hard bounds for tokens, retries, deadlines, concurrency, and estimated cost under normal and adverse inputs.

Failure containment20%

Provider and validation failures map to safe application outcomes without unbounded retries, leaked internals, or silent partial results.

Operational documentation10%

The note states assumptions, unsupported tasks, configuration ownership, privacy limits, and the deterministic fallback in reviewable language.

Lab 61000 planned XP

Retrieval-Augmented Generation

Build a grounded knowledge system from ingestion to retrieval, reranking, citations, and evaluation.

You will learn:
  • Build a versioned ingestion path that preserves source identity, effective date, language, access scope, content hash, and deletion behavior
  • Implement access-filtered retrieval, reranking, bounded context selection, abstention, and citation validation in the question-answering service
  • Evaluate retrieval relevance, answerability, groundedness, citation correctness, and conflicting or unanswerable cases on a labeled set
You'll build:Evaluated RAG question-answering service with citations

Lab assessment

80% pass threshold

Use an approved course corpus with stable source identifiers. Include answerable, unanswerable, stale, conflicting, permission-restricted, and prompt-injection cases.

Submission

Submit ingestion and service code, corpus manifest, retrieval configuration, labeled evaluation set, result report, sample cited answers, and threat notes.

Assessment rubric
Corpus and ingestion integrity20%

Every indexed chunk is traceable to a versioned source and access scope, with repeatable updates, deletion, and duplicate handling.

Retrieval and answer correctness30%

Permission filters precede retrieval, context remains within budget, answers follow supplied evidence, and unsupported questions trigger abstention.

Evaluation evidence25%

The labeled set covers stated risk cases and reports retrieval, answer, abstention, groundedness, and citation measures with inspected failures.

Citation quality15%

Displayed citations resolve to the exact supporting passage and effective source, while invalid or invented identifiers are rejected.

Security and limitations10%

The service resists cross-scope retrieval and document instructions, protects sensitive logs, and states corpus, freshness, and answerability limits.

Lab 7950 planned XP

Agents and Tool Use

Turn model output into controlled actions with typed tools, explicit state machines, budgets, timeouts, and approval boundaries.

You will learn:
  • Define an explicit state machine that separates deterministic workflow steps from model decisions and terminal states
  • Implement typed tools with server-side identity, authorization, idempotency, validation, minimal permissions, and mocked side effects
  • Demonstrate traces for success, refusal, invalid arguments, tool failure, repeated calls, exhausted budgets, timeout, and required human approval
You'll build:Bounded tool-using agent with an auditable execution trace

Lab assessment

80% pass threshold

Implement one bounded agent in a sandbox with no irreversible external side effects. Run the prescribed scenario suite and preserve redacted traces.

Submission

Submit the state diagram, tool schemas and authorization rules, runnable agent, scenario tests, redacted traces, and approval and recovery policy.

Assessment rubric
Orchestration model20%

States, transitions, stop conditions, retries, deadlines, budgets, and human gates are explicit, finite, and consistent with the implemented flow.

Tool boundary correctness30%

Schemas are precise, arguments are validated, authorization is enforced server-side, repeated requests are safe, and outputs are treated as untrusted.

Scenario and trace evidence25%

Automated scenarios prove expected state transitions and final outcomes, and each trace links model choice, tool request, approval, result, and error.

Side-effect and approval safety15%

Irreversible or high-impact actions are excluded or require informed approval, and cancellation, timeout, and partial failure leave a known recoverable state.

Auditability and data minimization10%

Trace fields support review without exposing secrets or unnecessary personal data, and retention and ownership are documented.

Lab 81100 planned XP

Production AI and Capstone

Evaluate AI systems like software, observe them in production, protect data and users, and assemble the complete capstone architecture.

You will learn:
  • Produce a bilingual service design that traces user journeys to data, model, tool, human-review, fallback, and tenant-isolation boundaries
  • Define offline and online quality gates, traces, service and model metrics, feedback handling, alert ownership, and recovery objectives
  • Demonstrate a delivery plan with privacy and security controls, staged release, incident exercises, rollback evidence, and explicit no-launch criteria
You'll build:Production-ready bilingual AI service design and delivery plan

Lab assessment

80% pass threshold

Synthesize the preceding work into one implementation-ready design for a bounded bilingual service. Resolve contradictions between quality, security, privacy, cost, and operations before recommending release.

Submission

Submit the architecture and data-flow diagrams, bilingual service contract, evaluation and observability plan, threat and privacy review, runbooks, staged delivery plan, and decision record.

Assessment rubric
End-to-end architecture25%

The design specifies identities, trust boundaries, data flows, model and tool contracts, human decisions, dependencies, failure paths, and ownership without hidden components.

Evaluation and operational evidence25%

Quality gates and observability connect representative offline cases to live service, model, safety, cost, and outcome measures with owners and thresholds.

Security, privacy, and governance25%

Controls cover least privilege, tenant isolation, secret handling, data minimization, retention, audit, abuse, approval, and incident responsibility.

Release, recovery, and limitations15%

The staged plan has measurable entry, stop, rollback, and no-launch criteria, and incident exercises demonstrate recoverable service states.

Bilingual service quality10%

Arabic and English journeys preserve equivalent decisions, evidence, errors, fallback, and escalation, with RTL and accessibility requirements ready for verification.

Target Competencies

🧠 ML Systems Foundations🧠 Deep Learning Implementation🤖 LLM Application Engineering⚙️ Production AI Design and Operations