Applied AI Engineer
Location: United Kingdom or Netherlands (Remote/Hybrid)
My client is an enterprise software company that is making a significant investment in AI-native products and building a team of Applied AI Engineers to help define the next generation of its platform.
This is a highly hands-on role focused on designing, building, deploying, and operating production AI systems. You'll own AI-powered product features end-to-end, working across application development, agent orchestration, retrieval systems, deployment, observability, and customer-facing implementation.
This is not a research role. We're looking for engineers who have shipped real AI products to real users and understand the challenges that come with operating them in production.
What You'll Do
- Build AI-powered product features from concept through production
- Design and deploy agentic systems, tool-calling workflows, and multi-step reasoning architectures
- Build and optimize RAG pipelines, retrieval systems, and knowledge architectures
- Develop evaluation frameworks and testing strategies for non-deterministic AI systems
- Work across the stack, including frontend, backend, infrastructure, and deployment
- Partner closely with product, engineering, and customers to deliver impactful AI capabilities
- Help establish best practices for production AI engineering across the organization
What We're Looking For
Production AI Experience
- Proven experience shipping LLM-powered products to production
- Experience operating AI systems at scale and managing real-world failure modes
- Strong understanding of model selection, prompting strategies, context management, and reliability
Agentic Systems & RAG
- Experience building agentic workflows and tool-calling systems
- Experience with frameworks such as LangGraph, CrewAI, AutoGen, or custom agent architectures
- Strong understanding of retrieval systems, embeddings, vector databases, hybrid search, and re-ranking
- Familiarity with GraphRAG is a plus
AI Evaluation & Observability
- Experience building evaluation frameworks for AI systems
- Familiarity with regression testing, LLM evaluation methodologies, and performance monitoring
- Experience with tools such as LangSmith, Langfuse, Braintrust, OpenTelemetry, or similar platforms
Engineering Fundamentals
- Strong Python development experience in production environments
- Experience with TypeScript, modern web frameworks, and API development
- Comfortable working with cloud infrastructure, containers, CI/CD pipelines, and Kubernetes
- Experience deploying and operating services in Azure environments is preferred
Ideal Background
We're particularly interested in engineers who have experience building customer-facing AI products, working closely with users, and owning systems from idea through production.
Experience in enterprise SaaS, industrial software, operations technology, maintenance platforms, or forward-deployed engineering environments is beneficial but not required.
What We're Not Looking For
- AI strategists without recent hands-on engineering experience
- Researchers without product or deployment experience
- Candidates whose experience is limited to demos, prototypes, hackathons, or internal chatbots
- Engineers who cannot clearly explain how they evaluate AI systems in production
If you're excited about building production AI products, working closely with customers, and helping shape an AI-native platform from the ground up, we'd love to hear from you.