AI Platform Engineer

Serviceplan Group

Job

In this role, you lead the development and operation of a cloud environment for AI applications, create CI/CD pipelines, integrate data sources, and implement monitoring tools to ensure system quality.

Job summary

This listing has been machine translated. Show original

Job technologies

Your role in the team

  • The AI Platform Engineer (all genders) is the person who builds and operates the foundation: the cloud environment, the model gateway, and the data integration on which knowledge bases, retrieval, and agents ultimately run.
  • You work closely with colleagues who, based on this foundation, build the actual retrieval and agent systems – your platform is their foundation.
  • You bring several years of experience, with which you make independent decisions, take responsibility for a system as a whole, and stand by the consequences of your decisions.
  • Operate cloud infrastructure. You are responsible for Infrastructure-as-Code, CI/CD, as well as security and networking fundamentals of the platform on a hyperscaler of your choice (AWS, Azure, or GCP).
  • Operate model gateways. You build and manage the integration of our language models, both open and proprietary, including routing, fallbacks, and cost control.
  • Integrate data sources. You build ingestion pipelines and data contracts that reliably connect new sources (e.g., DAM, CMS, Adtech/Martech) to the knowledge and retrieval layer, in close coordination with colleagues who are responsible for our data platform in the long term.
  • Set up observability infrastructure. You provide the tracing and monitoring tooling that continuously measures quality, costs, and latency.
  • Make decisions responsibly. You independently make technical decisions regarding stack, costs, and scaling, openly communicate trade-offs, and advocate for them with stakeholders.
  • Ensure collaboration. You coordinate closely with colleagues who build retrieval and agent systems on your infrastructure to ensure smooth handovers.

Our expectations of you

Qualifications

  • You develop production-grade software, ideally in Python, and are familiar with containerization and microservice architectures.
  • You have a basic understanding of RAG and agent systems: enough to design infrastructure that effectively supports vector databases, agent runtimes, and retrieval workloads.
  • You can substantiate technical decisions convincingly, openly discuss trade-offs, and stand by the consequences of your decisions.
  • You are accustomed to taking end-to-end responsibility for a system, even without someone already providing you with the architecture.
  • You are curious, quickly acquire new tools and concepts, and want to develop visibly.

Experience

  • You have 5-8 years of experience in cloud, platform, or infrastructure engineering, including several years of hands-on experience in production.
  • You have several years of practical experience with a hyperscaler (AWS, Azure, or GCP) - cloud services, Infrastructure-as-Code, CI/CD, security and networking fundamentals, Kubernetes or managed Kubernetes.
  • You have experience with ingestion and orchestration tools, data contracts, and the fundamentals of lineage and data freshness — enough to connect data sources cleanly to a knowledge layer.

What we offer

  • Responsibility for infrastructure that is truly in production, with direct relevance to the group's AI future.
  • Proximity to decisions regarding models, architecture, and data strategy.
  • An environment that challenges you technically and where good ideas quickly become real systems.
  • Space for you to develop further towards platform architecture or technical leadership, depending on where you want to go.

Benefits

Topics you will work on

Job locations

Map of the job locations
© OpenMapTiles, © OpenStreetMap contributors
  • Location Munich
    Bayern, Germany

About your employer

Since our founding in 2002, we have specialized in performance-oriented online, social and content campaigns. Based on this wealth of experience, we have further developed into a 360 ° planning media agency in 2018. With the view from the digital perspective on the classical media, we work out cross-media and data-based mediastrategies for our customers.

Company size
250+ Employees
Company type
Established Company
Work model
Full Remote, Hybrid, Onsite
Industry
Advertising, Marketing, PR
  • Tröger & Cie. AktiengesellschaftNuremberg, Regensburg, Bayreuth

    • Easy Apply
    • Hybrid
    • Onsite
    • Full Time

    Anyone who joins here not only designs software – they bring machines to life that are recognizable on real construction sites. Software Developer (m/f/d) Basic Engineering Our client is an internationally leading manufacturer of technically...

    • Ethernet
    • C
    • Git
    • Python
    • Bash
    • Linux
    • C++
    • CAN
    • J1939
    • +4
    • +5
  • WebslineSalzburg, Freilassing

    • Hybrid
    • Onsite
    • Full Time
    • Senior

    You actively shape the technical development of our software products and influence their long-term architecture. You develop our core applications primarily using C# as the central programming language and technological foundation. You design, develop,...

    • C#
    • JavaScript
    • SQL
    • CSS
    • HTML5
    • AJAX
    • MS SQL-Server
    • +2
    • +3
  • Öko-Institut Consult gGmbHFreiburg im Breisgau, Berlin

    • Easy Apply
    • Hybrid
    • Onsite
    • Part Time/Full Time

    Operation, monitoring, and further development of the network infrastructure. Administration and configuration of firewalls, routers, and switches. Ensuring network availability, performance, and security. Participation in IT security concepts and...

    • TCP/IP
    • Active Directory
    • Windows
    • Microsoft Exchange
    • Office 365
    • Linux
    • VLAN
    • +4

AI Platform Engineer

Serviceplan Group