Design, implement, and maintain AI-powered applications for a European energy transmission operator, leveraging large language models, retrieval-augmented generation, multi-agent workflows, and cloud-native architectures to ensure reliable, secure, and scalable solutions."
Key responsibilities
Design and implement AI-powered applications using large language models, retrieval-augmented generation, and agentic workflow patterns.
Build backend services, APIs, and integrations to support AI-centric solutions.
Design and optimize retrieval pipelines, including embeddings, vector search, hybrid search, metadata filtering, and reranking.
Define safe usage patterns for AI tools, human-in-the-loop processes, and agent behaviors.
Support selection and benchmarking of models and frameworks based on quality, cost, latency, maintainability, and security.
Troubleshoot issues including hallucinations, retrieval errors, latency spikes, cost inefficiencies, and unreliable outputs.
Develop reliable AI orchestration workflows by integrating LLM APIs and workflow frameworks.
Implement evaluation, testing, monitoring, and observability mechanisms for AI applications.
Collaborate with fellow engineers and product or business stakeholders to align technical solutions with requirements.
Skills and competences
Software engineering best practices
Backend development
API design and integration
Retrieval pipeline design
AI workflow orchestration
Observability and monitoring implementation
AI application evaluation methods
Security best practices for sensitive data
Cloud-native application development
Technical communication of trade-offs
Cross-functional collaboration
Pragmatic problem-solving
Qualifications
5+ years of software engineering experience
1+ year of integrating generative AI or LLM services into applications
Fluency in English
Fluency in French or Dutch
