About Us
We are a well-established Belgian company in the insurance sector. Our flagship product is a SaaS platform used by insurance brokers, backed by over 20 years of success and a highly efficient, robust codebase built primarily in .NET.
We are currently in a strategic phase of innovation, integrating Artificial Intelligence to revolutionize how our users interact with our platform. To achieve this, we are building an ecosystem of Python microservices that communicate with our core system via APIs, and we are looking to expand our AI team to accelerate this journey.
The Role
You will join a growing Artificial Intelligence team, working closely with our AI Specialist. Your primary mission will be to design, develop, and deploy Generative AI solutions that deliver direct value to our users and optimize internal processes.
This is not just an R&D or experimental role; we have an ambitious roadmap to launch these new AI features into production. Our SaaS is used daily by thousands of professionals as their primary work tool. This means you will tackle real-world challenges related to high volume, scale, and performance, taking your code from development straight to the end-user.
You will have end-to-end ownership of your development lifecycle, supported by our Infrastructure and DevOps team.
What you will do in your day-to-day
* Develop and implement AI-driven features, such as intelligent email analysis, automated data extraction from documents, conversational assistants, and complex RAG systems.
* Build and maintain efficient, scalable microservices in Python using FastAPI.
* Apply Prompt Engineering techniques, build RAG architectures, and integrate LLMs using frameworks like LangChain and LangGraph.
* Design and implement robust LLM evaluation pipelines to ensure the quality, accuracy, and reliability of our generative models in production, leveraging observability tools like LangFuse.
* Collaborate closely with the .NET development team to ensure seamless integration of AI services via APIs.
* Engage with technical and business stakeholders to understand requirements and translate user needs into technical solutions.
* Explore and evaluate new AI technologies, with the potential to dive into model fine-tuning and traditional Machine Learning in the future.
* Manage the deployment and monitoring of your services in Azure, taking end-to-end responsibility with the backing of our infrastructure team.
What we are looking for
* Demonstrable Mid-level experience in software engineering, with a strong focus on Python and API development (FastAPI).
* Hands-on experience working with Large Language Models (LLMs), RAG architectures, and Prompt Engineering.
* Familiarity with the Generative AI ecosystem and tooling; specifically, practical knowledge of frameworks like LangChain/LangGraph and monitoring/evaluation tools like LangFuse.
* Experience working with cloud providers, preferably Azure (and familiarity with tools like Azure AI Foundry).
* A strong "get things done" and product-oriented mentality. You are driven by shipping features to production, adding tangible value to customers, gathering real-world feedback, and iteratively improving the product.
* An inquisitive, adaptable mindset with a strong capacity to learn and stay continuously up-to-date with the latest trends, tools, and breakthroughs in the rapidly evolving AI landscape.
* Excellent communication skills to interact effectively with various stakeholders across the company.
Nice-to-haves
* Knowledge or familiarity with .NET/C# to better understand the core of our platform.
* Previous experience with fine-tuning open-source models or traditional Machine Learning.
* Familiarity with LLM evaluation methodologies.