AI Engineer: GenAI, RAG & Production Specialist (Hybrid)

Koda Tech; Brussel Hoofdstad; Hybrid; EUR 85.000 - 110.000; Vollzeit

Zusammenfassung

Koda Tech is seeking a Freelance AI Engineer to join Brussels on a 12‑month contract in a hybrid setup. You will build next‑gen AI products, GenAI capabilities, and production‑grade AI solutions.

You will design and deploy RAG pipelines, APIs, and backend services, collaborating with data engineers and product teams to move AI prototypes into production while optimizing model performance and governance.

Qualifikationen

• 3+ years' experience in AI/ML with production exposure.
• Strong Python development skills.
• Hands-on with Generative AI, LLMs, and RAG architectures.
• Experience with SQL and large-scale datasets.
• Familiarity with vector DBs, embeddings, prompt engineering.
• Experience building APIs and deploying AI into production.
• Hands-on with AI governance practices.

Aufgaben

• Design and develop AI-powered applications using Python, LLMs, and GenAI technologies
• Build and optimise RAG pipelines leveraging vector databases and semantic search
• Develop APIs and backend services to integrate AI capabilities into existing platforms
• Work closely with Data Engineers, Software Engineers, and Product teams to take AI solutions from prototype to production
• Fine-tune, evaluate, and improve LLM performance, accuracy, and reliability
• Implement prompt engineering, model orchestration, and AI governance best practices
• Contribute to the evolution of the client's AI Innovation Lab and help shape future AI initiatives

Kenntnisse

Python

Generative AI / LLMs

RAG pipelines

SQL

Vector databases

Embeddings

Prompt engineering

API development

Production deployment

LangChain/Azure OpenAI

Tools

LangChain

Azure OpenAI

OpenAI

LangGraph

Jobbeschreibung

Koda Tech is seeking a Freelance AI Engineer to join Brussels on a 12‑month contract in a hybrid setup. You will build next‑gen AI products, GenAI capabilities, and production‑grade AI solutions.

You will design and deploy RAG pipelines, APIs, and backend services, collaborating with data engineers and product teams to move AI prototypes into production while optimizing model performance and governance.