Full-Stack Engineer (AI-Native) - AgentX

Who we are

AgentX is a platform for building and running production AI agents. It powers real businesses — including KsięgoBoty, a live AI platform used daily by Polish accounting firms with paying clients. We're not a demo. We ship, customers pay, and the roadmap is driven by what actually moves their work forward.

We're small, agile, and allergic to ceremony.

Who we're looking for

A builder who thinks about problems, not tickets.

If you need a Jira board with acceptance criteria, three rounds of grooming, and a PM to tell you what "done" means — this isn't for you, and that's fine.

If instead you read a Slack message like "accountants are losing 2 hours a day reconciling this" and your brain immediately jumps to "okay, what does the user actually need, what's the simplest thing that works, and how do we ship it" - keep reading.

You'll own problems end-to-end. Frontend, backend, the LLM layer, the deploy, the follow-up when a customer hits something weird. You decide what to build, you build it, you ship it, you watch what happens.

You also understand that what you ship matters to real people. Customers have real deadlines, real stress, real businesses. This isn't code for code's sake :) 

What "AI-native" actually means here

Not "I've used ChatGPT." We mean:

• You treat Claude / Cursor / Codex / whatever-comes-next as a core part of how you work, not a gimmick

• You have opinions on when to use an agent vs. a single call, structured output vs. free-form, RAG vs. fine-tuning vs. just-a-better-prompt

• You can tell when a model is the wrong tool for the job and reach for plain code instead

• You're excited about what AI lets you build -1 but you don't fetishize it. The model is a tool. The problem being solved is the product.

The stack (roughly)

Full-stack TypeScript / React on the frontend, Go and Python on the backend, LLM orchestration (Anthropic / OpenAI / LiveKit for voice), Postgres, AWS. You don't need to have touched all of it — you need to be the kind of engineer who picks up unfamiliar pieces quickly and confidently.

What you'll actually do

• Ship features that customers see in hours, not quarters

• Design AI workflows that work in production, not just in demos

• Kill your own darlings when data says the feature isn't working

• Push back on the founder when he's wrong (he will be, regularly)

How we work

Fast pace, but Monday to Friday. Weekends are yours. We don't crunch, we don't fake urgency, we don't do meetings that could've been a message. We'd rather ship steadily for years than sprint for six months and lose you.

What we offer

• Real ownership of real product areas — not a seat on a feature factory

• A codebase where decisions are made by whoever's closest to the problem

• Direct line to the founder, customers, and the money side of the business

• Flexible hours, flexible setup, remote-friendly

• Compensation that reflects seniority and the fact that we actually value shipping

How the process works

1. You send us stuff

• Your CV — yes, we read them

• One thing you built end-to-end you're proud of — and what you'd change about it today

• One AI product (yours or someone else's) you think is genuinely good, and why

• Your take: an accounting firm says our agent is "mostly right but wrong in ways that scare them." What do you do first?

2. We actually read it — and reply within 2-3 days

No black hole. Either we say "let's talk" or we say "not this time, here's why."

3. We meet and see if there's a vibe

30-45 min call. You meet the founder, we talk about your work, you ask us hard questions. If the chemistry isn't there — no hard feelings, better to know now.

4. Problem-solving session (top 2-3 candidates)

We give you a real problem we're working on. You come back with how you'd approach it — your thinking, your questions, your trade-offs. We're not watching over your shoulder, we're not timing you, we're not asking you to reverse a binary tree. We want to see how you think.

5. Decision

We tell you yes or no within 2-3 days of the session. If yes - you start when you're ready. Tomorrow, next week, after your notice period. Your call.

📧 seb@agentx.so

Skip the "passionate team player" opener. Show us how you think.