Level
Senior
Location
Stuttgart
Working Model
Hybrid, Onsite
Job Field
IT, DevOps, Back End
Employment Type
Full Time
Contract Type
Permanent employment

Job Summary

In this role, you design scalable infrastructures for AI systems, lead optimization projects, and implement FinOps strategies for cost reduction and security across various cloud environments.

Job Technologies

vLLM

Your role in the team

Enterprise AI Operations: You design and oversee the globally scalable operational infrastructure (infrastructure design) for mission-critical AI systems.
High-End Optimization: You lead complex inference optimization projects, establish advanced quantization methods, and minimize system latencies.
Global FinOps Governance: You implement company-wide policies for budget control and cost efficiency in the area of compute-intensive AI applications.
Security & Observability: You ensure that all systems meet the highest standards for data security and compliance through comprehensive monitoring and tracing.
Mentoring & Teamlead: You lead the LLMOps team professionally, drive technical standardization forward, and advise the client architects at eye level.

This text has been machine translated. Show original

Our expectations of you

Education

Proficient in German (very good) and English (fluent), with a completed IT degree.

Qualifications

Expertise in architecture and operation of globally scalable enterprise cloud infrastructures (multi-cloud, hybrid) for mission-critical AI systems.
LLMOps at enterprise level: end-to-end tracing, continuous evaluation, monitoring, automated test pipelines, and governance interfaces.
Performance and inference tuning of LLMs in production (quantization, GPU utilization, serving optimization via vLLM).
Excellent knowledge in establishing company-wide AI FinOps strategies for continuous cost control and optimization.
Security and compliance standards (enterprise security, API security, encryption) for highly sensitive corporate data.
Ownership: You take responsibility for the operational stability and strategic architectural decisions of highly available AI infrastructures.
Strategic foresight: You recognize technology trends early and translate them into future-proof, stable operational concepts.
Knowledge Multiplier: You love actively sharing your knowledge with the team and explaining complex infrastructure topics in an understandable way.

Experience

Experience in leading DevOps / Platform Engineering teams and defining technical standards.

This text has been machine translated. Show original

What we offer

You can work in a role-based company.
You will find open corporate communication and short decision-making paths with us.
An extensive and tailored onboarding program is ready to ensure your optimal start at BCM.
Colleagues at eye level and our HR development support you in advancing both professionally and personally to the next level.
You mainly work remotely and enjoy maximum flexibility.
Depending on the project, you are ready to support our clients remotely or on-site.
Unforgettable employee events: monthly team activities and a BCM vacation in summer.
BCM strengthens your balance, whether work or life, we always stand behind you.
Casual or suit? Office or home office? Early bird or night owl? You decide, with us you have the freedom to work in the way that suits you best.
You kick off the weekend with our BCM Community with a (hoppy) refreshing drink.