Hands-on AI Engineer

Antwerp – Hybrid

Yields is a fast-growing tech company at the forefront of Model Risk Management and AI Governance. Our SaaS platform helps organizations govern and monitor algorithms with transparency and compliance, from traditional risk models to modern AI systems. Trusted by leading firms worldwide, we empower teams to reduce risk, accelerate innovation, and stay ahead of evolving regulations like the EU AI Act.

We’re looking for a hands-on AI Engineer to help us scale real-world generative AI into our SaaS product. You’ll be our go-to expert on LLMs, embeddings, RAG, and context strategies, building abstractions and integrations that allow us to deliver secure, intelligent, and user-centric AI features.

This role is not about research experiments. It’s about building production-grade AI assistants that directly power our customers’ workflows — and laying the foundation of our future AI platform.

Design & Build AI Assistants: Deliver production-ready contextual AI assistants that interact with structured and unstructured data to enhance customer workflows.

Build & Integrate: Orchestrate LLM-powered assistants in our SaaS product. Connect APIs, manage data flow, and ensure smooth backend/frontend integration and performance.

Context & Prompting: Develop strategies for prompt templates, context injection, RAG pipelines, and embeddings to deliver accurate, user-aligned AI output across multiple LLM providers.

Platform Abstractions: Implement provider-agnostic frameworks (e.g. LangChain, LangGraph, LangSmith) to flexibly switch between models and scale securely.

Security & Multi-Tenancy: Ensure AI assistants respect RBAC and privacy requirements in a multi-tenant SaaS environment.

Collaboration: Work cross-functionally with engineers, DevOps, and business stakeholders to bring AI features from concept to customer-ready reality.

Continuous Learning: Stay on top of emerging AI technologies (e.g. model context protocols, new retrieval frameworks) and bring insights into the product.

• Proven experience building and deploying contextual AI assistants in production environments.
  
• Strong knowledge of LLMs, embeddings, RAG, prompting, and context strategies.
  
• Hands-on experience with LangChain, LangGraph, LangSmith or similar AI integration frameworks.
  
• Solid engineering background: backend/API integration, SQL databases, and SaaS systems.
  
• Experience designing abstractions across multiple LLM providers.
  
• Understanding of multi-tenant SaaS security and RBAC principles.
  
• Ability to collaborate with cross-functional teams and balance business needs with technical execution.

• Knowledge of AI governance and data privacy best practices.
  
• Familiarity with DevOps workflows (CI/CD, pipelines, deployments).