Senior AI Engineer

Intro

Are you passionate about building production-grade AI systems that solve real business problems? Do you have hands-on experience with LLM-powered applications and want to scale them to enterprise customers? Can you design intelligent agent systems and deploy them in a regulated industry?

Then you're the AI engineer we're looking for! Join us in transforming our internal AI Assistant into a multi-tenant SaaS product for insurance companies.

The Journey

We've built an agentic, RAG-based AI Assistant for Adcubum employees that has proven its value internally. Now we're taking the next step: transforming it into an external SaaS product for insurance companies.

As we establish our AI capabilities, you'll also help us explore and build further AI-powered solutions for the insurance industry - from automation to intelligent decision support.

You will collaborate with a team that combines insurance domain expertise, product knowledge, and technical depth. Together, you'll work directly with product management and insurance companies to turn our internal solution into a customer-ready SaaS product.

What We're Building

• Multi-agent AI system with intelligent orchestration
• RAG pipelines integrating multiple knowledge sources (documentation, APIs, databases)
• Multi-tenant SaaS architecture for insurance companies
• Production-grade deployment with enterprise security and compliance
  
  

Support you'll have: You'll work closely with our experienced platform and DevOps teams for Azure infrastructure setup and deployment automation - but you should understand these concepts and contribute to architectural decisions.

Tasks

Core AI Engineering Focus

• Design and implement RAG pipelines with semantic search and knowledge retrieval
• Build multi-agent orchestration systems with intelligent query routing
• Integrate multiple LLM providers (Azure OpenAI, AWS Bedrock) and develop prompt engineering strategies
• Develop specialized knowledge base indexers for documentation, code, and business data
• Implement vector search combined with structured database queries
• Build REST APIs and integrate Model Context Protocol (MCP)
• Optimize AI system performance, accuracy, and cost efficiency
  
  

Production & Platform Collaboration

• Collaborate with platform team on multi-tenant architecture design
• Contribute to Azure/AWS deployment decisions
• Implement monitoring, logging, and observability for AI components
• Work on containerization and deployment automation
• Support security, authentication, and compliance requirements
• Participate in customer discussions to understand requirements and iterate on solutions
  
  

Requirements

Must-Have Technical Skills:

• 3+ years of software engineering experience with strong Python backend development
• Hands-on experience building LLM-powered applications in production
• Practical experience with either:
  • RAG systems (Retrieval-Augmented Generation), OR
  • Other production ML/AI systems with real user impact
• Working knowledge of vector databases and embedding models
• Understanding of agent-based systems, multi-step AI workflows, or complex prompt engineering
• Experience with cloud platforms (Azure or AWS) - at least one production deployment
• Solid API design and development skills (REST, OpenAPI, async patterns)
• Basic understanding of containers and CI/CD concepts
  

Strong Advantages

• Experience scaling AI systems to multi-tenant SaaS products
• Knowledge of Kubernetes or managed container services (AKS, EKS, ECS)
• Familiarity with Infrastructure as Code (such as Terraform)
• Understanding of Model Context Protocol (MCP)
• Node.js/TypeScript experience for full-stack integration work
  
  

Education & Languages

• Bachelor's degree in Computer Science, AI/ML, or equivalent practical experience
• English language skills (fluent) - our product and customer communication is in English
  
  

Personal Skills

• Self-starter with ownership mentality: You like to see projects through from concept to production
• Pragmatic problem-solver: You balance quality with speed to market and make thoughtful technical decisions
• Comfortable with ambiguity: You thrive in environments where not everything is defined and you help shape the direction
• Team-oriented collaborator: You work effectively with domain experts, consultants, and customers who may not be technical
• Curious and learning-focused: AI/ML technology evolves rapidly - you stay current and love experimenting
• Customer-minded: You understand that technology serves business needs and enjoy seeing real-world impact
  
  

Benefits

• End-to-end ownership: Shape a product from internal tool to external SaaS - your decisions matter
• Modern AI/ML stack: Work with cutting-edge technologies (multi-agent systems, RAG, latest LLMs)
• Small, high-impact team: Work directly with domain experts, product management, and customers
• Technical growth: Expand both your AI/ML expertise and cloud/platform engineering skills
• Production impact: Build systems used by insurance companies with thousands of users
• Professional development opportunities: Conferences, training, certifications in AI/ML space
• Collaborative environment: Learn from insurance domain experts while contributing technical expertise
• Flexible working arrangements: Modern work culture with flexibility
• Competitive compensation package: Aligned with your experience and the Croatian market
• International exposure: Work with teams across Switzerland, Germany, and Croatia
  
  

Want to build production AI systems for insurance companies?

Join us in Zagreb and help transform how insurance companies leverage AI technology!