Olten
AI Site Reliability Engineer (m/f/d)
- 04 August 2026
- 80 – 100%
- Permanent position
- English (Fluent)
- Olten
About the job
We have developed a web-based online platform for job searching and talent acquisition that digitalises the
application process and supports companies in quickly recognising talents in the market and securing them for the long term. With a digital Rocken profile, every
applicant can quickly and easily connect with market-leading companies and share their profile.
Our work places people at the centre, both technologically and organically. Rocken® offers
executive search and talent management consulting to address the personal and individual needs
of each person and to implement these optimally in recruitment and career planning.
AI Site Reliability Engineer (m/f/d)
Are you looking for a challenge in the financial sector where precision and discretion are central? Our Rocken partner is an established private bank with a strong international focus. The institution combines traditional values with contemporary solutions and manages demanding client relationships worldwide. The focus is on customised asset management and strategic financial advice. Employees operate in an environment that demands the highest quality standards while fostering entrepreneurial thinking. Flat hierarchies and short decision-making paths characterise the daily work routine. Professional excellence is valued here as much as the ability to build and maintain long-term client relationships. Collaboration takes place in interdisciplinary teams with a clear focus on sustainable results. Are you ready to bring your expertise into a demanding environment? Then we look forward to connecting you with our Rocken partner.Responsibilities:
You design and develop scalable AI infrastructure services optimised for GPU workloads
In this role, you implement and manage enterprise AI platforms (e.g. Kubernetes, OpenShift) for model inference
You operate and maintain high-performance HPC clusters with bare-metal and virtual GPU servers
You analyse and resolve complex infrastructure incidents across hardware and software stacks
In this role, you support data science teams in providing the required infrastructure
Qualifications:
You have an educational qualification in computer science.
You have at least 5 years of experience in IT system administration, including over 3 years with Linux (preferably RHEL) and solid scripting skills in Shell, Python, and Ansible.
You bring deep knowledge of GPU topologies and architectures (e.g. NVLink, PCIe switching) as well as container orchestration with Kubernetes, Terraform, and ArgoCD, and have initial practical experience with Prometheus, Grafana, and DCGM Exporter.
You work according to ITIL methods, act proactively and responsibly, and convince with strong analytical skills and solution-oriented thinking.
You keep an overview even under time pressure, skilfully set priorities, and reliably deliver high-quality results.
You communicate fluently in English; German skills are a plus.
ROCKEN Jobs:
https://rocken.jobs
Create profile:
https://rocken.jobs/application/profil-erstellen/
Work location
Olten
Contact
Diego Barth,
+41443852145
