AI Operations and Inference Specialist

Overview

AI Operations and Inference Specialist role at DESY in Hamburg. DESY is one of the world’s leading research centres with a focus on decoding the structure and function of matter, from elementary particles to the building blocks of life. DESY IT is establishing a dedicated AI team to deploy and optimize locally hosted AI inference services and chatbot applications across the supporting infrastructure for PETRA IV and related operations.

About your role

• Evaluate, test, and implement AI frameworks, tools, workflows, and infrastructures suited for operating locally hosted generative AI services (ChatBot and inference solutions)
• Design and configure inference backends, ensuring optimal deployment configurations and performance
• Integrate into existing HPC-based GPU infrastructure the appropriate front-end and back-end technologies for providing robust, user-friendly, and reliable generative AI applications
• Conduct performance assessments and optimization, leveraging available local high-performance computing (HPC) and powerful GPU-based infrastructure
• Provide operational support, including troubleshooting, debugging, and enhancing service reliability across various AI models and authentication frameworks
• Collaborate with other team members, and document implemented systems and operational processes

Benefits

Look forward to a unique working environment on our international research campus. DESY offers flexible working hours, part-time and job-sharing options, mobile work (up to 50%), a family-friendly atmosphere, health management, an occupational pension, and a secure public-sector employment. Remuneration follows TV-AVH regulations plus a Deutschland-Ticket subsidy at both locations.

About you

• You have completed a university degree in computer science, engineering, or comparable knowledge
• You have hands-on experience operating Linux environments for data-intensive workloads; container technologies and GPU familiarity are a plus
• You have experience with AI inference solutions, ideally leveraging inference backends
• Proficiency in Python and experience with API-driven AI solutions are desirable
• Familiarity with generative AI frameworks and models
• A collaborative mindset and ability to work in an international, interdisciplinary team
• Good command of German, both written and spoken, is advantageous

Contact

For further information, please contact Yves Kemp at ‑2318 ( ).

Please submit your complete application documents (letter of motivation, CV and relevant certificates).

We look forward to receiving your application via our application portal.

DESY promotes equal opportunities and diversity. We strongly encourage women to apply. Applications from severely disabled persons will be given preference if equally qualified (sbv.desy.de).

You can find further information here:

Details

• Seniority level: Associate
• Employment type: Full-time
• Job function: Education
• Industries: Research Services