AI Engineer (freelance)

We are looking for an AI Engineer who can translate Generative AI and Large Language Model capabilities into reliable, real-world solutions. This role focuses on delivering scalable systems, integrating advanced language technologies, and ensuring responsible, safe deployment. You will work closely with engineering, data, and product teams to move projects from concept to production, shaping high-impact AI features across the organisation.Project information: Duration: 6 months to begin withWorking style: HybridAssignment type: FreelanceWork location: Rotterdam/The HagueResponsibilities: • Integrate LLM and Generative AI capabilities into existing products and platforms• Build, test, and deploy AI solutions from prototype to production• Collaborate with software engineers, DevOps, and product teams throughout delivery• Develop LLM-powered features such as chatbots, copilots, summarisation, and Q&A tools• Implement Retrieval-Augmented Generation solutions using enterprise and domain-specific data• Apply AI safety practices including guardrails, content filtering, and prompt validation• Optimise prompts and workflows for performance, reliability, and accuracy• Establish evaluation pipelines to track relevance, quality, drift, and user impact• Monitor production systems to detect degradation and ensure consistent model behaviour• Contribute to continuous improvement of AI engineering standards and deployment practicesRequirements: • Strong programming experience in Python with solid knowledge of NumPy, Pandas, and SQL• Experience deploying models using Flask, FastAPI, or MLflow• Familiarity with model serving environments such as Triton or Hugging Face endpoints• Practical experience integrating APIs such as OpenAI, Anthropic, Cohere, or Mistral• Hands-on use of frameworks such as LangChain or LlamaIndex• Knowledge of vector databases including FAISS, Weaviate, Pinecone, or Qdrant• Understanding of RAG architectures and how to combine LLMs with enterprise data• Experience with MLOps practices including versioning, monitoring, and logging• Awareness of bias detection, mitigation techniques, explainability, and transparency• Understanding of LLM safety practices including hallucination mitigation and guardrail design• Experience working in Azure cloud environments• Ability to build MVPs and deliver production-ready AI features• Practical knowledge of machine learning and LLM principles to support integration and scaling• Experience with evaluation metrics, automated testing, and A/B experiments for GenAI features• Background in trading or carbon markets is a plus but not required• Experience with common GenAI use cases such as assistants, copilots, summarisation, Q&A, or content generation