Sr. Full-Stack Engineer, AI-Native (LATAM / Europe - Remote)

Braintrust; Polska; Hybrid; PLN 320,000 - 420,000; Full time

Job summary

Reunion Marketing is seeking a senior full-stack engineer who embraces AI coding assistants as a core part of building, testing, and shipping production code.

You will own end-to-end features across databases, APIs, and front ends while upholding security and reliability. The role emphasizes working with AI tooling to accelerate delivery and maintain high-quality software for automotive dealer clients.

Qualifications

• 6+ years of full-stack software engineering experience.
• Experience with TypeScript, React, Node.js or Python, and SQL in production systems.
• Hands-on experience with AI coding assistants like Claude Code, Cursor, or GitHub Copilot.
• Ability to ship production software with AI-assisted workflows.
• Strong architectural and debugging skills.

Responsibilities

• Own features end to end from database to front end.
• Apply AI-assisted development practices and maintain code quality.
• Collaborate on AI-powered product features and data pipelines.
• Ensure testing, security, and multi-tenant data access standards.
• Improve reliability, monitoring, and incident response.

Skills

TypeScript

React

Node.js

Python

SQL

AI-enabled development

Tools

Claude Code

Cursor

GitHub Copilot

Job description

You will build and ship features across the full stack of Reunion Marketing's products, from the database and APIs to the interfaces our teams and automotive dealer clients use every day. We are looking for a senior full-stack engineer who uses AI coding assistants as a core part of how they build, ships production code at a pace that would not be possible without them, and still owns the quality, security, and design of everything that goes out.

About This Role

Reunion Marketing builds the platforms and AI products that our strategists and automotive dealer clients rely on, including the Altitude Intelligence platform. Our engineers build with AI coding assistants such as Claude Code as a standard part of the workflow, from prototype to production. This role works across three areas:

• Client-facing applications
• Dashboards, reports, and tools that dealer clients and our teams use daily
• Every screen and every number has to be right in front of a client
• Platform and data services
• APIs, integrations, and data pipelines behind our marketing product lines
• Every product and report depends on this data being complete and correct
• AI-powered features
• Chat, report generation, and agentic workflows built on large language models
• Turns client data and our methodology into answers and next steps

You will own features end to end, and the defining questions are yours:

• How should this be built across the stack, and what is the simplest design that will hold up?
• Which parts of the work should an AI coding assistant do, and what must a person write or check?
• How do we know AI-generated code is correct, secure, and maintainable before it ships?
• What does "ready for clients" mean — and how do we prove it?

It is a senior, hands‑on role with unusual visibility: what you ship either protects a client relationship, wins one, or grows one, and we expect engineering decisions to be made with that in mind.

The opportunity

• Production data at scale. Live performance data across five marketing product lines for hundreds of automotive dealerships, not a demonstration dataset.
• Daily users who depend on the output. Strategists, client success, sales, and external clients use what you build as part of their working day.
• Meaningful stakes. A bug does not stay inside a demo; it can reach a client conversation. The engineering standard follows from that.
• Genuine ownership. The product direction is set and shipping, and many architectural decisions, including how the team builds with AI coding assistants, are still open for this hire to make and defend.

The perspective we expect

• Understand where each piece of work fits in the product and what it changes for our clients and teams — retention, expansion, hours returned — and let that understanding shape the engineering decisions.
• See the system end to end: how a schema choice shows up in a report, how an API change lands in a client conversation, how today's shortcut becomes next quarter's incident.
• Treat AI-generated code as a draft from a fast collaborator: useful, and always reviewed, tested, and understood before it ships.
• Explain technical trade-offs to strategists and executives in their terms, and be willing to defend a delayed release when shipping would put client trust at risk.
• Judge their own success by what ships, how reliably it runs, and the time it returns to our teams and clients.

What You’ll Own

• Full-stack feature delivery — features from the database schema and APIs through to the front end, built with AI coding assistants and held to production standards for testing, security, and multi-tenant data access.
• AI-assisted engineering practice — how the team uses Claude Code and similar tools day to day: project context and instruction files, custom commands and agents, review conventions, and the guardrails that keep generated code consistent with our architecture.
• AI-powered product features — chat, report generation, and agentic workflows built on large language models, including retrieval, tool use, structured outputs, and the evaluations that show they are accurate.
• Quality and testing — automated tests, CI gating, and code review that catch defects whether a person or an assistant wrote the code.
• Production reliability — monitoring, incident response, performance, and the rollbacks that follow. We expect instrumentation before conjecture, and decisions in writing.
• Architectural judgment — build versus buy, iteration speed versus client-safe controls, and where AI tooling helps versus where it adds risk. Well-supported positions are expected; unsupported ones are not.

What We’re Looking For

• 6+ years of full-stack software engineering experience, including 1+ year building production software with AI coding assistants such as Claude Code, Cursor, or GitHub Copilot as a primary part of your workflow. Occasional autocomplete use does not meet this bar.
• Strength across a modern web stack (for example TypeScript, React, Node.js or Python, and SQL), with a record of well-structured production systems rather than glue scripts.
• Deep, hands‑on experience with AI coding assistants: structuring context for large codebases, writing project instructions and custom commands, running agentic multi‑step tasks, reviewing and correcting generated code, and knowing when to stop and write it yourself.
• A feature you shipped substantially with an AI coding assistant, and the ability to walk through how you directed the work, what the assistant got wrong, and how you caught it.
• Production debugging instincts — specific failures you have fixed across the front end, back end, and data layer, and a habit of instrumenting before guessing.
• A record of owning the quality bar on a multi‑team product, including incident response, rolling back a bad release, and defending a delayed release to stakeholders who wanted to ship.
• Strong written and architectural communication — a one‑page proposal that a strategist, another engineer, and a CTO can all read and respond to.

Nice to have

• Experience with Anthropic Claude specifically, including Claude Code, the Claude API, tool use, and prompt caching.
• Production experience building LLM features: prompt design, structured outputs, tool use, retrieval, and evaluation.
• Domain experience in marketing analytics, SEO/SEM, paid media, local search, or answer‑engine visibility.
• Experience building a system of record that an organization runs on, rather than a feature inside one.

How We Work

• Decisions are written. Architectural choices come with a short proposal, the alternatives considered, and the evidence.
• Tests and evaluations are first‑class. No feature ships without them, and no regression is acceptable because it is old.
• The human is in the loop by design. AI assistants write a large share of our code, and a person still owns every change: they direct the work, review it, and answer it in production.
• Pace follows risk. We move quickly where the cost of being wrong is low, and deliberately where the result reaches a client. We expect this hire to know the difference.

How Success Is Measured

Success in this role shows up in what you ship and how reliably it runs, in adoption by the teams and clients it serves, in the time it returns to our strategists, in how well the team builds with AI tools because of your work, and in the absence of defects reaching a client.

Hiring process

• Introductory call (30 minutes) — mutual fit, your background, and your questions.
• Technical deep dive (60–90 minutes) — a walkthrough of a production system you built end to end, covering:
  • how you used AI coding assistants to build it: what you delegated, how you directed and reviewed the work, and what you would change.
  • a failure you debugged in production: what your instrumentation indicated, what your instinct suggested, and which proved right.
  • a release you held back and defended to stakeholders who wanted to ship.
  • an architectural decision across the stack, and the business reasoning behind it.
• Working session with the team — a real problem from our domain, worked through together using your usual AI coding tools.
• Offer.

Candidates who can speak to those four experiences concretely can expect the process to move quickly.