Playbook · Building with AI

Updated

What does a full-stack AI engineer do?

A full-stack AI engineer builds the whole product around an AI model: the screens, the API, the database, the model calls, and the limits that keep cost and mistakes in check. Think of a full-stack developer who ships AI features. Training the models is a researcher’s job.

In Stack Overflow’s 2025 survey, 27% of respondents call themselves full-stack developers, the largest group by far. Only 1.4% call themselves AI/ML engineers.
Source: Stack Overflow Developer Survey 2025, fielded 29 May to 23 Jun 2025

From my work

At Peeps, an Overwolf app, I planned the project, built the architecture and wrote the core in TypeScript, with a team of three: one QA, one backend developer, and me on full-stack. We built on Overwolf’s API and its app starters to save time. When the investors moved the deadline from six months to four, we cut features and shipped them after launch.

EZ Chat is my own product on the same platform. It shows the whole job end to end, because I own every part of it.

What a full-stack AI engineer builds

  • The front end that shows AI output, including loading, streaming and the error state nobody draws in the mockup.
  • The API layer that holds the keys, calls the model and checks the output before anyone sees it.
  • The database that stores what was asked, what came back, and who used how much.
  • Payments and limits, so one curious user can’t run up your API bill over a weekend.
  • Monitoring for cost per user, failed calls and bad answers.
  • Tests that rerun when you change a prompt or a model. A one-word prompt change is still a change.

How it differs from an ML engineer

An ML engineer trains and tunes models, builds data pipelines and measures model quality. A full-stack AI engineer uses models through an API, from OpenAI, Anthropic or Google, or the ones that run on the phone, and builds the product people pay for.

Most startups adding AI to a product need the second. If the model itself is your product, hire the first.

My record as a full-stack AI engineer

  • 7+ years of full-stack work, fully remote since 2019: TypeScript, React, Next.js, Angular, Node.js, NestJS and PostgreSQL.
  • EZ Chat, my own product: an Overwolf app, live on the Overwolf store, that lets online gamers translate chats with other players into the language they choose. TypeScript and TailwindCSS on the Overwolf API, a back end on Supabase Edge Functions (Deno) with PostgreSQL migrations, the OpenAI API for the translation, and paid subscriptions through Tebex with validated webhooks.
  • A client product, as tech lead at PixelConn: integrated the OpenAI API into a React and Node.js product on AWS Serverless with PostgreSQL, Neo4j and GraphQL.
  • The Merchant Engine, my self-hostable e-commerce platform: a NestJS and Prisma API on PostgreSQL, Redis and BullMQ queues, an Angular 21 admin and an Analog.js storefront, covered by Jest, Vitest, Playwright and Lighthouse CI.
  • Claude Code in my work.
  • A bachelor’s in computer science, a 3-year program covering software development and AI fundamentals.

When you need an ML engineer instead

Training models from scratch, data science projects and AI research are a different job. For those, hire an ML engineer or a research team.

How to hire one

One person who owns both the app and the AI part saves you the handoff between “the AI person” and “the app person”, and the meeting where each explains why the bug belongs to the other.

I work inside your team on the Full plan, $4,995 a month: one task at a time, worked on every working day, with a call whenever you need one. Your standups, your tools, your repo, on CET hours that overlap with US mornings. Billed monthly, pause or cancel anytime. I sell this, so read it with that in mind.

If you only need one AI feature added to an app you already have, it is done on a monthly plan, one task at a time: Limited at $1,995 a month or Full at $4,995. Both are a flat monthly price, pause or cancel anytime. On the Full plan it usually ships within the first month.

Read next

Sources

Start

Find out what stands between you and launch.

Start the 14-day Trial: your problems ranked in the first 5 business days, then fixes for what fits in the 14 days. Not ready yet? Ask for a free teardown.

Start the 14-day Trial · $995

Secure checkout via Stripe · Refund policy

Founding rate: the first 3 clients get 20% off, in return for a named testimonial and a case study. On a monthly plan, the 20% applies to the first month.

Prefer to talk first? Book 30 min or email badii@badii.studio

Free teardown

48h · max 5 / week

A 5 to 10 min recorded review of your live app's public surface. No access needed, just the URL.

I use these details only to reply and record your teardown, and delete them after 12 months. Privacy