AI Engineer (Product-focused)

Startup Atlas; Rotterdam; Hybride; EUR 70 000 - 120 000; Plein temps

Avantages offerts par ce poste

Competitive compensation

Employee benefits

Office in Rotterdam

Résumé du poste

Zeno, Rotterdam-based startup, is looking for an AI Engineer (Product-focused) to own AI-driven product capabilities end-to-end. You will work at the application layer between models and users, crafting reliable AI behavior, retrieval pipelines, and guardrails to deliver high-trust workflows for legal professionals.

You will collaborate with Data, Legal, and GTM teams, ship fast, and own critical product surfaces with a focus on quality and user trust.

Qualifications

• 4+ years of product-focused full-stack engineering experience.
• Strong backend design in Python and API orchestration.
• Experience deploying AI-native systems in production.
• Familiar with Pydantic and structured schemas for model-app interfaces.

Responsabilités

• Own AI product surfaces end-to-end from concept to shipped feature.
• Build and evolve the AI application layer with prompts, outputs, and retrieval.
• Design safeguards and predictable behavior for enterprise-grade use.
• Develop high-accuracy context construction and relevance controls.
• Move fast with clean abstractions and minimal hacks.

Connaissances

Product-focused engineering

Backend Python (Litestar)

AI-native systems

Pydantic / structured schemas

Frontend React/Vue + TypeScript

API design and data models

Retrieval pipelines / LLM tooling

Ownership / cross-functional collab

Outils

Litestar (Python web framework)

PydanticAI

React

TypeScript

Description du poste

The intelligence engine for legal work, providing AI-powered legal research, contract review, risk assessment, and drafting tools for in-house legal teams.

As an AI Engineer (Product-focused) at Zeno, you’ll own AI-driven product capabilities end-to-end, working at the application layer to design and build systems between models and users. You’ll engineer reliable AI behaviors, build retrieval systems, and ship fast while ensuring quality in a legal AI startup.

Job Description

Application-layer, Senior / Product-driven

We usually respond within three days

We’re building a world‑class team to redefine knowledge work with AI

Zeno is a legal AI startup building a platform that helps lawyers research, review, and draft documents with real legal reasoning — not just text prediction. We’re developing technology that can:

• Search and retrieve statutes, case law, and commentary with high precision.
• Reason step‑by‑step, applying legal tests and weighing precedents.
• Explain every answer transparently, so lawyers can trace conclusions back to the exact sources.

Where most tools automate surface‑level tasks, we’re focused on replicating the way lawyers actually think through legal problems, making depth and trust the foundation of everything we build.

You’re joining an early‑stage startup that is already working with leading firms. Backed with €3M in seed funding, we’re now scaling a team of engineers and thinkers who want to solve real problems, drive innovation, and create lasting change in the legal sector.

The Role

As an AI Engineer (Product-focused) at Zeno, you’ll own AI‑driven product capabilities end‑to‑end. You’ll work at the application layer of AI: designing and building the systems that sit between models and users. This is where correctness, structure, and product judgment matter more than clever prompts. You’ll work closely with Data, Legal, and GTM to turn probabilistic model output into software professionals can trust in real, high‑stakes workflows.

If you like shipping fast, care deeply about quality, and want real ownership over meaningful AI product surfaces, this role will stretch you in the right ways.

What you will be doing

• Own AI product surfaces end‑to‑end
  Take responsibility for a concrete AI capabilities (e.g. drafting, revision, reasoning workflows) and drive it from concept to shipped product to iteration.
• Engineer the AI application layer
  Build and evolve prompt logic, structured outputs, retrieval pipelines, tool interfaces, state management, and guardrails as real product code.
• Turn probabilistic systems into dependable behavior
  Design system boundaries, constraints, fallbacks, and patterns that make AI behavior predictable, explainable, and safe.
• Build high‑accuracy context and retrieval systems
  Design and implement context construction, document selection, chunking strategies, and relevance controls.
• Ship fast without accumulating AI debt
  Move quickly with discipline: clean abstractions, versioned behavior, reusable patterns, and minimal one‑off hacks.

What we’re looking for

• 4+ years of experience in product‑focused full‑stack engineering, ideally in a fast‑growing SaaS or complex domain.
• Strong backend engineering skills
  You’re comfortable designing APIs, data models, and orchestration layers in Python (Litestar) and care about correctness and maintainability.
• Experience building AI‑native systems in production
  You’ve worked with LLMs beyond demos: structured outputs, retrieval, tool use, evaluations, monitoring, and iteration based on real feedback.
• Familiarity with modern AI tooling
  Experience with Pydantic (including PydanticAI), structured schemas, and type‑safe interfaces between models and application code is a strong plus.
• Solid frontend literacy
  Experience with React or Vue, TypeScript, and modern UI patterns. You don’t need to be a design wizard, but you can ship complete features.
• High product sense and judgment
  You think in terms of user trust, edge cases, and long‑term system behavior, not just technical feasibility.
• Bias toward ownership
  You take responsibility for outcomes, not just implementation.

Who you are

• You’re more interested in making AI usable and reliable than in chasing the latest model release.
• You want ownership over critical product surfaces, not a narrow slice of infra.
• You enjoy working in small, serious teams where judgment and taste matter.
• You believe the most important AI work right now is turning intelligence into software people can rely on.

The ride from startup to scale‑up

Things will break, priorities will shift, and there won’t always be a playbook. You’ll wear multiple hats, ship fast, and learn faster. Some weeks will feel chaotic, some problems will feel bigger than your role. That’s the nature of the ride from startup to scale‑up: if you need stability and structure, this won’t fit. But if you thrive on ownership, speed, and building from zero, you’ll love it here.

• Be part of a product‑driven team reinventing how legal professionals work.
• Join early and shape the foundation of a fast‑growing, high‑impact startup.
• Work in a place where hierarchy doesn’t matter — only the best ideas do.
• Collaborate with a top‑tier team of engineers, researchers, and entrepreneurs.
• Competitive compensation, employee benefits and strong upside as we grow.
• An inspiring place to work in the heart of Rotterdam.