Full Stack AI Engineer
Ship the entire product — interface, API, and the AI layer.
You want to build and launch complete AI products on your own.
- 01Design, build and deploy a complete product on your own
- 02Add retrieval-backed AI features that hold up under real use
- 03Own the database, the API, the interface and the pipeline that ships them
Your Full Stack AI Engineer career begins
Most engineers can build a screen, or an endpoint, or a prompt. Very few can take an idea and stand up the whole thing — the interface someone uses, the API behind it, the database under that, and an AI feature that holds up when real people push on it.
This track is that whole path, in order. You start with the web platform and TypeScript, move through React and Next.js, build real backends against PostgreSQL, then add the AI layer: retrieval over your own data, streaming responses, tool calls, and the evaluation that stops a feature shipping broken.
It is the widest of the four tracks and the one to pick if you are not sure. Everything an AI Engineer learns about working on top of foundation models is here — with the product engineering around it that turns a notebook into something people can log into.
The superset track: everything an AI Engineer does, plus the product around it.
The Full Stack AI Engineer job
- Build user-facing features end to end, from the interface to the database
- Design APIs and data models other engineers build against
- Add AI features to an existing product and keep them reliable
- Own deployment, monitoring, and the incidents that follow
- Early-stage startups where one engineer owns a whole product
- Product companies building AI features into an existing app
- Agencies and consultancies shipping client products
- Anyone hiring a founding or first engineer
- 1Junior Full Stack Engineer — Ships features inside an existing codebase.
- 2Full Stack / Product Engineer — Owns features end to end, interface to database.
- 3Senior Product Engineer — Sets the architecture and mentors the team.
- 4Founding / Staff Engineer — Owns the whole system and what gets built next.
Every skill in the track, in the order you learn it.
7 phases, 132 named skills. Not chapter headings — the individual things you will be able to do by the end.
- PHASE 1 OF 718 SKILLS
The web platform and TypeScript
The layer everything else sits on, learned properly rather than picked up by accident.
- Semantic HTML
- Flexbox and grid layout
- Responsive breakpoints
- Scope and closures
- ES modules
- DOM and event delegation
- Promises and async/await
- The event loop
- Fetch and HTTP verbs
- Status codes and headers
- Types and interfaces
- Unions and narrowing
- Generics
- Utility types
- Strict mode and tsconfig
- npm, pnpm and lockfiles
- Git branching and rebasing
- Browser dev tools
- PHASE 2 OF 722 SKILLS
Frontend engineering with React and Next.js
Interfaces that stay fast and accessible as they grow.
- Components and props
- useState and useEffect
- useRef and useMemo
- Custom hooks
- Lists, keys and reconciliation
- Controlled forms
- Schema validation
- Client data fetching
- Caching and revalidation
- Context and reducers
- Next.js App Router
- Layouts and nested routes
- Server vs client components
- SSR, SSG and ISR
- Streaming and Suspense
- Route handlers
- Server actions
- Design tokens
- ARIA and focus management
- Keyboard navigation
- Core Web Vitals
- Image and font optimisation
- PHASE 3 OF 723 SKILLS
Backend engineering and databases
APIs and data models that survive contact with production.
- REST resource design
- API versioning
- Node.js runtime
- Express and Fastify
- Middleware pipelines
- Request validation
- Error handling
- Relational modelling
- Normalisation
- Types and constraints
- Indexes and query plans
- Reading EXPLAIN output
- Transactions and isolation
- ORMs and query builders
- Migrations
- Zero-downtime schema changes
- Redis caching
- Cache invalidation
- Background jobs and queues
- File uploads and object storage
- Pagination and N+1 queries
- WebSockets
- Server-sent events
- PHASE 4 OF 720 SKILLS
Authentication, security and payments
The parts that get a product taken seriously — or breached.
- Sessions vs tokens
- JWTs
- Refresh token rotation
- Reuse detection
- OAuth 2.0
- OpenID Connect
- Password hashing
- Email verification
- Password reset flows
- Role-based access control
- CORS
- CSRF
- XSS
- SQL injection
- Rate limiting
- Secrets management
- Subscription billing
- Webhook signatures
- Idempotency keys
- Audit logs
- PHASE 5 OF 720 SKILLS
The AI layer
Adding intelligence to a product without making it unreliable.
- LLM API fundamentals
- Model selection
- System prompts
- Few-shot examples
- Structured outputs
- JSON schema enforcement
- Tool calling
- Response streaming
- Embeddings
- Vector storage with pgvector
- Document chunking
- Retrieval tuning
- RAG pipelines
- Citations and grounding
- Conversation memory
- Token budgets
- Cost attribution
- Fallbacks and degradation
- Evaluating a feature
- Prompt injection defence
- PHASE 6 OF 712 SKILLS
Testing and code quality
The habits that let you change a codebase months later without fear.
- Unit testing
- Integration testing
- End-to-end testing
- Test doubles and mocking
- Testing React components
- API contract tests
- Coverage and what it misses
- Linting and formatting
- Type-safe API clients
- Reading and giving code review
- Refactoring safely
- Debugging methodically
- PHASE 7 OF 717 SKILLS
Ship it and operate it
From a local dev server to something on a real domain that stays up.
- Docker images
- Multi-stage builds
- docker compose
- CI with GitHub Actions
- Preview deployments
- Release strategy
- Platform and cloud hosting
- Build vs runtime config
- CDNs and cache headers
- Structured logging
- Error tracking
- Uptime monitoring
- Alerting and on-call basics
- Product analytics
- SEO and metadata
- Open Graph and sitemaps
- Cost monitoring
6 projects. Every one of them a running system.
Not exercises with a known answer. Each project is something you can deploy, send someone a link to, and defend in an interview.
A responsive marketing site with a real content source
Build and deploy a multi-page site driven by structured content, with proper metadata, images, and accessibility — the project that proves you can finish something and put it online.
A REST API with authentication and PostgreSQL
A service with real users: registration, email verification, login, refresh token rotation, and role-based access over a relational schema you designed.
A real-time collaborative board
Multiple people editing the same data at once, with optimistic updates, conflict handling, and presence — where you learn what state management is actually for.
An AI document assistant with citations
Upload documents, ask questions, get streamed answers that cite the passage they came from — a full retrieval pipeline wired into a product interface.
A subscription SaaS with billing and an admin panel
Plans, checkout, webhooks, entitlements, and an internal admin surface — the commercial machinery a product needs before it can take money.
A production AI product, shipped end to end
Your own idea taken all the way: designed, built, tested, containerised, deployed behind CI/CD on a real domain, with logging, error tracking, and cost monitoring in place.
Full Stack Engineer · Product Engineer (AI) · Founding Engineer
From first lesson to signed offer.
Learn
Work through the curriculum in order, from the fundamentals to the applied work the role does every day. Written lessons, not video you cannot search.
Build
Ship the projects. Each one is a real system with real constraints, and each one ends up somewhere you can show it.
Practice
Solve problems in the DSA arena, take AI mock interviews, and get feedback on the answers you actually gave.
Get hired
Build an ATS-ready resume, see how well you match each opening, close the gaps it finds, and apply without leaving the platform.
Questions people ask before starting.
Do I need to know how to code before starting?
No. The track opens with the web platform and JavaScript from the beginning. If you already know those, the onboarding questions place you further in rather than making you repeat them.
How is this different from the AI Engineer track?
AI Engineer goes deeper on the model layer — retrieval, agents, evaluation, and production reliability. This track covers that layer too, but spends the first half on the product engineering around it: interfaces, APIs, databases, auth, and billing. Pick this one if you want to build whole products; pick AI Engineer if you want to specialise in the AI itself.
Do I need to learn Python as well?
Not for this track. It is TypeScript end to end, which is how most product teams ship AI features. The AI Engineer and ML Engineer tracks are the Python-first ones.
Will the projects be good enough for a portfolio?
They are built to be. Each one is a running application rather than a repository — deployed, with a URL you can send someone, which is the thing hiring managers actually check.
Can I switch tracks later?
Yes. Your track is an answer you give at signup and can change at any time, and the shared core — data structures, system design, Git, Docker — carries across all four.
The other three tracks.
AI Engineer
Build products on top of foundation models.
You want to build with large language models, not train them.
Not model training or research — that is the ML Engineer track.
You will build- A prompt workbench with structured outputs
- Semantic search over a document collection
- A production RAG assistant with citations
Roles: AI Engineer · GenAI Engineer · LLM Application Engineer
Explore this track→ML Engineer
Train, serve, and monitor models in production.
You want to own models end to end, from raw dataset to live endpoint.
Not calling somebody else’s API — here you build and own the model.
You will build- An end-to-end tabular model with an honest evaluation
- An image classifier fine-tuned from a pretrained backbone
- A reproducible training pipeline with tracked experiments
Roles: Machine Learning Engineer · MLOps Engineer · Applied ML Engineer
Explore this track→Data Engineer
Move and model data at scale.
You want to build the pipelines every other team depends on.
Not dashboards and analysis — you build the systems those run on.
You will build- An analytics layer over a raw dataset
- An incremental ingestion job with tests
- A batch ELT pipeline: orchestration, transformation, warehouse
Roles: Data Engineer · Analytics Engineer · Data Platform Engineer
Explore this track→Everything you need to grow as an engineer — software engineering, AI, real-world projects, technical challenges, hands-on practice, AI-powered guidance, interview preparation, and career development.
Don’t just learn engineering. Experience it.
Learn. Build. Solve. Practice. Prepare. Get hired.