AI Solutions Engineer (BE-CSS-ISA-2026-115-LD)

Contribute to the AI-driven evolution of the BE-CSS group’s software product portfolio, identifying and implementing opportunities to embed AI capabilities across group applications. Design and develop LLM-based solutions, including a first-line support chatbot backed by retrieval-augmented generation (RAG) pipelines, vector databases, and secure knowledge connectors, in close collaboration with the CERN IT department providing the underlying MLOPs substrate. Join the ATS AI Core Team and take a major role in the rollout of LLM/agentic AI and knowledge systems, contributing to reusable patterns, evaluation frameworks, and safe agent deployment practices across the sector. Collaborate with engineers, domain experts, and scientists from across CERN —including CERN IT, BE-CSS colleagues, and other ATS groups — to align AI solutions with operational needs and organisational standards. Contribute to other AI-related initiatives in the BE-CSS group and across the ATS sector, sharing expertise and adapting to emerging priorities in the rapidly evolving field of applied AI. Help define and deliver the central AI infrastructure needed across ATS, contributing to shared tooling, reference architectures, MLOps practices, and evaluation frameworks that enable groups to adopt AI solutions safely and efficiently.

At CERN, the European Organization for Nuclear Research, physicists and engineers are probing the fundamental structure of the universe. Using the world's largest and most complex scientific instruments, they study the basic constituents of matter - fundamental particles that are made to collide together at close to the speed of light. The process gives physicists clues about how particles interact, and provides insights into the fundamental laws of nature.

• Master's Degree or equivalent relevant experience in the field of Computer Science or a related field.

• Solid experience in Python software development, including the design and delivery of production-ready applications in a collaborative engineering environment.

• Practical knowledge of LLM frameworks (such as LangChain or LlamaIndex) and hands-on experience building retrieval-augmented generation (RAG) pipelines and working with vector databases, chunking and embedding techniques.

• Familiarity with agentic AI orchestration approaches and the Model Context Protocol (MCP), or a strong motivation and demonstrated ability to develop this expertise rapidly.

• Understanding of evaluation and safety frameworks for LLM-based systems, including techniques for assessing reliability, output quality, and responsible deployment.

• Experience with MLOps practices and CI/CD workflows; ability to write clear technical documentation and communicate complex ideas to diverse audiences.

• Ability to build effective working relationships and communicate clearly with colleagues from diverse scientific and engineering backgrounds, including non-specialist audiences.

• Curiosity about the application of AI in complex scientific and operational environments, with an openness to learning the accelerator domain context through direct engagement with its challenges.