AI Engineer

Our client is a growing Swiss technology company that develops modern systems in a security-relevant future market. The focus is on self-controlled technologies, high availability, secure infrastructure, and innovative solutions without cloud dependence. You can expect a technical environment with flat hierarchies, short decision-making paths, and plenty of room to actively shape the internal AI platform. The company offers • A full-time position with a workload of 80 to 100 percent • Workplace at the headquarters in Aadorf • An exciting task in the area of IT Services and local AI infrastructure • Consistent on-premise environment with a no-cloud approach • Work with open-source models, GPU systems, Docker, and modern inference stacks • Plenty of room for performance optimization, automation, monitoring, and MLOps • Flat hierarchies, clear goals, and modern technologies • Flexible working hours with flexible working time • Attractive compensation and growing social benefits • Support for relevant further education and certifications • An environment where innovation and own ideas are actively promoted • Discounted fitness subscription directly next to the office • Free coffee for all employees • Regular team events, apéros, and joint meals • A long-term perspective in an exciting future market Our client wishes • In-depth experience with AI systems, large language models, or comparable machine learning applications • Good understanding of the operation of local or self-hosted AI models • Experience with Docker, containerized environments, and Linux systems • Experience with GPU-based workloads and performance optimization • Understanding of inference, model parameters, context lengths, quantization, resource consumption, and latency • Experience with open-source models and systematic evaluation of new models • Interest in MLOps, monitoring, automation, and productive operation of AI systems • Ability to critically test models and assess their benefits for specific applications • Understanding of interfaces, APIs, and the integration of AI into existing applications • Awareness of data protection, security, and the operation of sensitive systems without cloud dependence • Structured, independent, and solution-oriented work • Enjoyment of trying out new technologies and pragmatically transferring them into stable solutions • Very good German language skills • Good English language skills are an advantage • Experience with OpenLLM, vLLM, SGLang, or comparable inference frameworks is an advantage • Experience with n8n, workflow automation, or AI-supported process chains is an advantage • Knowledge of Python, APIs, scripting, or backend integration is an advantage • Experience with GPU hardware, drivers, CUDA, VRAM management, or hardware evaluation is an advantage • Experience with retrieval-augmented generation, embeddings, or internal knowledge systems is an advantage What to expect • You operate, maintain, and optimize a local AI cluster • You work with containerized AI models and GPU-supported systems • You ensure that local models run stably, quickly, and with high availability • You evaluate new open-source models and test their usability • You compare models in terms of performance, quality, resource consumption, and stability • You find suitable parameterizations and automate testing and optimization processes • You maintain central AI interfaces and make them available for internal applications • You work with inference stacks like vLLM, SGLang, or alternative solutions • You integrate AI functions into internal tools, chat applications, development workflows, and automation processes • You support AI-based development and programming processes in the company • You work with automation solutions and AI integrations • You build monitoring for models, clusters, resources, performance, and availability • You work according to MLOps principles and support the productive lifecycle of AI models • You document models, configurations, interfaces, and operating processes in a traceable manner • You participate in the evaluation of new hardware and specialized GPU systems • You support the assembly, configuration, and expansion of local AI systems • You actively contribute to the further development of the AI platform and internal AI strategy