AI Engineer

Position Overview

We are looking for an AI Engineer with 3-5 years of experience to help maintain and evolve our fleet of AI agents, LLM-as-a-judge systems, and other AI-powered tools used by healthcare, life sciences, and marketing teams. This role will work closely with senior engineers on graph design and with product and research teams to define what “a good answer” means, including grounding, coverage, and citation honesty.

The AI Engineer will contribute to the continued development of these systems by improving tools, retrieval and citations, agent architecture, and overall system speed, cost, and accuracy. They will also support evaluations and experiments that help us understand and improve system performance.

We are looking for someone with strong Python skills and a solid understanding of LLM systems who is excited to continue growing their technical depth. At this level, the engineer should be comfortable owning a component of a production service from design through testing and review, while partnering with more senior engineers on broader architecture and system design.

Responsibilities

Agent tools: Create new agent tools and improve existing ones across retrieval and grounding, vector and keyword search, live-source search, analytics queries, PDF generation, and more. Integrate external APIs and data sources into our agent systems, including Pinecone, Meilisearch, Hasura, Cube, and GCP.

Graphs and middleware: Extend and improve our agent state machines, including skill resolution, tool-calling loops, review gates, answer post-processing, and token guards.

Observability and operations: Work with real production data and infrastructure and help improve the observability, reliability, and ongoing maintenance of our AI systems.

End-to-end ownership: Own features from design and implementation through testing, deployment, and production support.

Qualifications

3-5 years of hands-on engineering experience, ideally working with data and/or AI systems.

Professional experience writing and testing Python.

Experience integrating APIs, including reading documentation and working with pagination, timeouts, authentication, and complex JSON responses.

Experience using LLMs as a developer and an interest in building reliable AI systems, including addressing issues such as hallucinations, incorrect citations, and context limitations.

Ability to write high-quality code using AI-assisted development tools such as Cursor, Codex, or Claude Code, or willingness to learn quickly.

Comfort working with production systems and taking ownership of features through implementation, testing, and deployment.

Nice to have

Hands-on experience with async Python in production (asyncio, aiohttp, or similar).

Familiarity with LangChain, LangGraph, or another agent or tool-calling framework.

Knowledge of search and RAG concepts, including embeddings, filters, and hybrid keyword and vector retrieval.

Exposure to GraphQL or analytics APIs, such as Cube or similar semantic layers.

Understanding of logs, traces, observability, and general maintenance of production systems.

Comfort contributing to frontend-adjacent work when needed.

Why Join Us?

Small team energy, big company support

High-impact work, early responsibility-you’ll contribute from day one

A learning-first culture-mentorship, peer support, and space to grow

A genuinely fun, curious environment-we take the work seriously, not ourselves

Strategy meets creativity-where insight, brand, and behavior collide

A future-facing mission-everything we do aims to improve lives

If you're ready to bring curiosity, strategy, and creativity together to reimagine healthcare-and make a real difference to people’s lives, let’s talk.

Salary range: €35,000-55,000/year