Agoya

Careers

All roles

AI Engineer

Open

We’re looking for an AI Engineer to join our team Agoya HQ in Belgium and strengthen our Generative AI delivery. You’ll work in a hybrid setup and collaborate closely with AI Engineers, Data Engineers, and domain stakeholders to design, test, and continuously improve prompt strategies that power real business workflows. This is a hands-on role for someone who enjoys the final-mile work that turns prototypes into products: evaluation, iteration, traceability, and operationalizing LLM + retrieval patterns in real workflows.

BelgiumPermanentSenior

Your responsibilities

  • Build and improve LLM-powered workflows end-to-end, with a strong focus on the “last mile” (quality, reliability, and production readiness).
  • Build and operate solutions on Azure (incl. secure integrations, deployment and monitoring).
  • Set up and use LLM observability and evaluation tooling (e.g., Langfuse) to track quality and iterate reliably.
  • Design and iterate system instructions and interaction patterns for real use cases (including tool/function calling where relevant).
  • Improve quality through structured evaluation (A/B comparisons, evaluation sets, regression testing, versioning).
  • Collaborate on agentic setups and RAG (retrieval-augmented generation): retrieval quality, grounding, context construction, and orchestration.
  • Translate business needs into clear technical specifications, success metrics, and acceptance criteria.
  • Document learnings and best practices so teams can re-use and scale solutions.

Are you the one?

  • You have strong language skills and a solid engineering mindset around how information is retrieved, grounded, and used in LLM systems.
  • You understand RAG concepts and can reason about retrieval quality, grounding, and context construction.
  • You collaborate well with engineers and are comfortable reading code, logs, and technical documentation.
  • You have experience improving LLM application quality through experimentation (evaluation sets, regressions, prompt/system updates, or similar).
  • You enjoy the “last 10%” work: making solutions robust, consistent, and production-ready.
  • You have ~5+ years of professional experience (or equivalent depth through projects) in a role that involved applied AI delivery, NLP/GenAI, product experimentation, or adjacent engineering work.
  • You communicate clearly and proactively: you align with multiple stakeholders, reach out when needed, and bring structure while respecting an agile way of working.
  • You speak English (required) and Dutch or French (required).

Apply for this role

Send us your details and CV — no fluff, straight to our team.