Senior AI Engineer

Koda Tech; Antwerpen; On-site; EUR 90,000 - 120,000; Full time

Benefits offered by this job

Competitive salary

Comprehensive benefits package

Career progression

Modern working environment

Job summary

Koda Tech in Belgium is seeking a Senior AI Engineer to join a new AI Engineering team responsible for building the core intelligence layer powering AI applications, assistants and autonomous agents. This hands-on role focuses on production-grade AI systems rather than research.

You will design central AI services for reasoning, retrieval and action, collaborate across architects, software engineers and AI specialists, and contribute to a secure, scalable AI ecosystem with governance and

Qualifications

• 5+ years of commercial software engineering experience.
• 2+ years building and deploying AI or LLM-based applications in production environments.
• Strong Python development experience, ideally with FastAPI or similar frameworks.
• Experience with agentic AI frameworks such as LangChain, LangGraph, CrewAI or similar.
• Strong knowledge of Retrieval-Augmented Generation (RAG) architectures.
• Experience working with embeddings, vector databases and semantic search technologies.
• Understanding of prompt engineering, evaluation frameworks and LLM optimisation techniques.
• Experience deploying applications using containers and cloud-native technologies.
• Knowledge of software engineering best practices including testing, CI/CD and observability.
• Strong communication skills and the ability to work within cross-functional teams.
• Experience within financial services or other regulated environments.
• Understanding of AI security concepts including prompt injection, data protection and responsible AI.
• Experience with Elasticsearch, OpenSearch or vector database technologies.
• Knowledge of Kubernetes, OpenShift or container orchestration platforms.
• Experience building enterprise-grade AI platforms or internal AI products.

Responsibilities

• Design and develop agent-based AI systems using modern orchestration frameworks.
• Build and optimise Retrieval-Augmented Generation (RAG) pipelines using vector search and enterprise knowledge sources.
• Develop scalable backend services in Python and FastAPI.
• Implement AI governance, security controls and guardrails to ensure safe and responsible AI usage.
• Engineer integrations with multiple Large Language Models and AI providers.
• Develop evaluation frameworks, automated testing and monitoring solutions for AI applications.
• Create tooling for prompt management, model routing and AI service management.
• Collaborate with software engineering, architecture and product teams to translate AI concepts into production-ready solutions.
• Improve performance, reliability and scalability of AI services running in containerised environments.
• Contribute to architectural decisions and establish engineering best practices within the AI platform.

Skills

Python development

FastAPI

LangChain

LangGraph

CrewAI

LLM integration

RAG architectures

Embeddings

Vector databases

Prompt engineering

CI/CD

Observability

Cross-functional teamwork

Regulated environments

Kubernetes/OpenShift

Tools

Elasticsearch/OpenSearch

Container orchestration

Job description

A leading Belgian organisation is building a next-generation AI platform designed to enable employees to securely leverage artificial intelligence across the business. The platform will provide a centralised environment for developing, deploying and governing AI solutions, with a strong focus on scalability, security and responsible AI practices.

As a Senior AI Engineer, you will join a newly established AI Engineering team responsible for developing the core intelligence layer that powers AI applications, assistants and autonomous agents across the organisation.

This is a hands-on engineering role suited to someone who enjoys building production-grade AI systems rather than focusing solely on research.

The Role

You will be responsible for designing and developing the central AI services that enable intelligent applications to reason, retrieve information and take action.

Working closely with architects, software engineers and AI specialists, you will help create a secure and scalable AI ecosystem capable of supporting multiple business-critical use cases.

You will play a key role in building agent orchestration frameworks, retrieval systems, AI governance controls and evaluation frameworks that ensure AI solutions can be safely deployed into production environments.

Key Responsibilities

• Design and develop agent-based AI systems using modern orchestration frameworks.
• Build and optimise Retrieval-Augmented Generation (RAG) pipelines using vector search and enterprise knowledge sources.
• Develop scalable backend services in Python and FastAPI.
• Implement AI governance, security controls and guardrails to ensure safe and responsible AI usage.
• Engineer integrations with multiple Large Language Models and AI providers.
• Develop evaluation frameworks, automated testing and monitoring solutions for AI applications.
• Create tooling for prompt management, model routing and AI service management.
• Collaborate with software engineering, architecture and product teams to translate AI concepts into production-ready solutions.
• Improve performance, reliability and scalability of AI services running in containerised environments.
• Contribute to architectural decisions and establish engineering best practices within the AI platform.

Requirements

• 5+ years of commercial software engineering experience.
• Minimum 2 years building and deploying AI or LLM-based applications in production environments.
• Strong Python development experience, ideally with FastAPI or similar frameworks.
• Experience with agentic AI frameworks such as LangChain, LangGraph, CrewAI or similar.
• Strong knowledge of Retrieval-Augmented Generation (RAG) architectures.
• Experience working with embeddings, vector databases and semantic search technologies.
• Understanding of prompt engineering, evaluation frameworks and LLM optimisation techniques.
• Experience deploying applications using containers and cloud-native technologies.
• Knowledge of software engineering best practices including testing, CI/CD and observability.
• Strong communication skills and the ability to work within cross-functional teams.
• Experience within financial services or other regulated environments.
• Understanding of AI security concepts including prompt injection, data protection and responsible AI.
• Experience with Elasticsearch, OpenSearch or vector database technologies.
• Knowledge of Kubernetes, OpenShift or container orchestration platforms.
• Experience building enterprise-grade AI platforms or internal AI products.

What's on Offer

• Opportunity to join a high-impact AI transformation programme.
• Work on cutting-edge Generative AI and Agentic AI initiatives.
• Collaborate with experienced engineers, architects and AI specialists.
• Long-term career progression within a growing AI function.
• Significant ownership and influence over technical decisions.
• Competitive salary and comprehensive benefits package.
• Modern working environment with strong investment in innovation and technology.