[permanent] ai engineer

Werkgever:
Riverflex
Regio:
Amsterdam
 
Functieomschrijving

Build cutting-edge AI systems with real business impact

At Riverflex, we don’t just talk about AI—we build it. As an AI Engineer, you’ll be part of a small, high-impact team developing intelligent solutions that blend modern software engineering with state-of-the-art language models and machine learning techniques. You’ll help design and deploy scalable AI systems that power next-generation digital products for clients and internal tools. 

We’re looking for someone who deeply understands LLMs, core ML fundamentals, and AI engineering, knows how to turn theory into working code, and thrives at the intersection of product, data, and engineering. If you’ve led AI delivery, built GenAI apps, and know how to scale with quality—this role is for you. 

The Role

As a hands-on lead engineer, you’ll design and build AI-powered services using LLMs, modern orchestration frameworks, and robust engineering practices. You’ll partner closely with data, product, and software teams to integrate these systems into real-world applications. You’ll also play a key role in growing our AI expertise & capability, developing frameworks/accelerators/best practices/etc. and mentoring our AI engineers. 

Responsibilities

  • Build scalable AI and GenAI systems using transformer-based models (e.g. GPT, Mistral, Claude) and RAG architectures 

  • Design and implement ML/AI pipelines including model training, evaluation,prompt chaining, embedding retrieval, and context management (MCP protocols) 

  • Engineer modular, well-tested Python code for AI agents, APIs, and microservices 

  • Apply ML Ops practices for reproducible training, deployment, and monitoring of models in production 

  • Use orchestration tools (LangChain, Semantic Kernel, n8n) to implement agent workflows and end-to-end AI experiences 

  • Collaborate with product and engineering teams to integrate AI into user-facing applications 

  • Partner with data engineering to build feature stores, vector search capabilities, and serve curated data 

  • Optimize AI systems for cost, latency, and scalability across Azure infrastructure (e.g., Azure ML, Azure AI Services) 

  • Lead on best practices around prompt evaluation, testing, model performance monitoring, and human-in-the-loop feedback 

  • Mentor and guide teammates (internally and at clients) on AI Engineering 

  • Champion responsible AI design, including bias mitigation and data privacy safeguards 

  • Must-Haves

  • 7+ years of software or ML engineering experience, including 2+ years working on GenAI/LLM-based products 

  • Strong Python engineering skills (typing, testing, packaging, dependency management) 

  • Solid understanding of ML and NLP/LLM fundamentals—tokenization, attention, transformers, embeddings, supervised/unsupervised learning, etc. 

  • Hands-on experience building with LLMs, prompt chaining, and retrieval-augmented generation (RAG) 

  • Familiarity with Model Context Protocol (MCP) standards: schema design, context injection, context window management 

  • Experience with orchestration and agentic frameworks (LangChain, Semantic Kernel, GPT agents) 

  • Experience working in CI/CD environments with ML Ops tooling (e.g., MLflow, AzureML, Kubeflow) 

  • Deep understanding of API design, microservices, and distributed system architecture 

  • Experience deploying scalable workloads on cloud platforms (Azure preferred) using Docker/Kubernetes 

  • Proven experience mentoring engineers and leading technical workstreams 

  • Nice-to-Haves

  • Experience with vector databases (e.g., Pinecone, FAISS, Weaviate) 

  • Familiarity with serverless deployment patterns and infrastructure-as-code (e.g., Terraform, CDK) 

  • Exposure to human-in-the-loop feedback systems and ethical AI design 

  • Experience in AI governance, risk mitigation, and AI performance tuning 

  • Consulting or client-facing delivery experience in data/AI-driven environments 

  • What We Offer

  • 25 days off per year plus closure between Christmas and New Year's. 

  • Flexible remote work from abroad options for up to 6 weeks per year. 

  • Learning & Development budget, including full access to Udemy courses. 

  • Classpass membership to support well-being. 

  • Latest tech & tools, including home office budget and professional software subscriptions. 

  • Equity share scheme to give long-term team members ownership in Riverflex.

  • Why join Riverflex?

  • Be a Pioneer: Contribute to the development of Riverflex’s Software Engineering domain.

  • Impactful Work: Work on high-profile projects with major clients like IKEA and deliver tangible results.

  • Growth Opportunities: Gain exposure to advanced AI tools, machine learning, and enterprise-level software solutions in a dynamic environment.

  • Supportive Culture: Work in a team that values innovation, creativity, and continuous learning.

     Kernwoorden