Company Overview
Join our dedicated, fast-paced experimentation and innovation unit, where you'll leverage cutting-edge AI and LLM technologies. This is an exciting opportunity to develop solutions that genuinely empower communicators and support frontline workers, driving strategic impact and exploring the full potential of new technologies.
Responsibilities
- Design, develop, and maintain scalable and fault-tolerant backend services that power our AI applications
- Apply advanced prompt engineering techniques to optimize model performance, manage context windows, and ensure reliable, high-quality responses
- Implement model integration patterns to connect and orchestrate various external and internal services
- Develop Agent-to-Agent (A2A) protocol communication strategies for complex multi-agent architectures
- Implement systems for Managing Conversational Protocols (MCP servers) and Agent-to-Agent (A2A) protocol to handle and maintain long-running, stateful interactions
- Define and implement observability standards for AI applications, including metrics for latency, cost, token usage, drift, and user-perceived quality
- Implement logging, tracing, and monitoring tools to quickly diagnose and troubleshoot issues in the end-to-end AI pipeline
- Collaborate with ML Scientists and Data Scientists to transition prototypes and models into production-ready, high-availability services
- Ensure the security, reliability, and performance of all production systems
Requirements
- 6+ years of professional experience in backend software development
- Strong proficiency in Go and preferably Java/Kotlin
- Proven experience integrating various AI/ML models into production backend systems
- Practical experience with prompt engineering
- Experience with cloud platforms (AWS, GCP, or Azure) and containerization technologies (Docker, Kubernetes)
Preferred Experience
- Experience building backend systems designed for complex agentic workflows or long-running conversational states
- Familiarity with foundational LLM concepts such as retrieval-augmented generation (RAG)
- Practical experience developing or managing MCP servers (Managing Conversational Protocols)
- Familiarity with Agent-to-Agent (A2A) communication protocols and multi-agent system design
- Experience with event-driven architecture and message queues (e.g. Kafka)
Benefits
- Competitive Compensation - we offer attractive salary packages including LTIP (Long Term Incentive Plan)
- Flexibility - we offer flexible working time models and the option of hybrid work, and support this with a yearly flex work allowance of €1560
- Recharge - with 31 vacation days annually (incl. one floating holiday), plus pro rata fully paid Fridays off during August
- Wellbeing - Monthly Wellbeing Allowance €35, from fitness to mental health, hobbies to relaxation
- Support - we're offering a company pension scheme
- Volunteers Day - you'll get one day off per year for supporting a social project