Job
- Level
- Senior
- Job Field
- Software, Data
- Employment Type
- Full Time
- Contract Type
- Permanent employment
- Location
- Dresden
- Working Model
- Onsite
Job Summary
In this role, you design architecture for AI platforms, implement flexible infrastructure, and oversee the integration of models into production systems within high-security environments.
Job Technologies
Your role in the team
- Define end-to-end architecture for on-prem / air gapped AI platforms, including compute, storage, networking, and model serving layers.
- Design and implement portable AI infrastructure using open-source components (model serving, orchestration, vector storage, pipelines).
- Translate product requirements into scalable system architectures, including deployment topology and hardware sizing.
- Establish security, isolation, and resilience patterns for AI workloads in restricted environments.
- Own decisions on model hosting, orchestration, observability, and lifecycle management.
- Design and deploy agentic and multi-agent systems on top of production-grade infrastructure.
- Integrate reasoning, planning, and learning capabilities into reliable, observable, and maintainable systems.
- Collaborate with hardware, software, and data teams to ensure seamless deployment and usability in production environments.
- Drive integration of AI systems into existing products and workflows in semiconductor manufacturing.
- Continuously evaluate and adapt emerging AI and infrastructure technologies for real-world industrial use cases.
- Leiten Sie architektonische Entscheidungen im Bereich KI-Infrastruktur, Modellbereitstellung und Systementwicklung.
- Contribute to building internal standards and reusable components for AI engineering across the division.
This text has been machine translated. Show original
Our expectations of you
Education
- University degree in Computer Science, Electrical Engineering, or a related field.
Qualifications
- Expertise in deploying AI/ML systems in on-premise, air-gapped, or otherwise restricted environments.
- Ability to define and evaluate hardware requirements (GPU/CPU/memory/storage/networking) for AI workloads.
- Fluent communication in English.
- Vertrautheit mit der Zusammenstellung von AI-Stacks aus Open-Source-Komponenten anstelle der Nutzung von Managed Services ist von Vorteil.
- Understanding of semiconductor manufacturing processes and data pipelines is an advantage.
Experience
- Strong experience in solution architecture and system design for production-grade software systems.
- Hands-on experience with model serving and inference systems (e.g. vLLM or similar).
- Experience with distributed systems, high-performance computing, or data-intensive platforms.
- Experience with CI/CD and MLOps for offline or partially connected environments.
- Strong programming skills (Python required; experience with systems-level languages such as C/C++ or Rust is a plus).
- Experience building cloud-independent AI platforms or migrating workloads away from managed cloud services is an advantage.
- Experience with agent-based systems, reinforcement learning, or LLM-based applications is an advantage.
This text has been machine translated. Show original
What we offer
- We offer a competitive, family-friendly total rewards package.
- We design our programs to reflect our commitment to an inclusive environment, while ensuring we provide benefits that meet the diverse needs of our employees.
This text has been machine translated. Show original
Benefits
Work-Life-Integration
Health, Fitness & Fun
Higher Take-Home Pay
Topics You Will Work On
Job Locations
About Your Employer
Kla Corporation
KLA Corporation is one of the world's leading companies in the development, manufacture and marketing of control and improvement methods for semiconductor production processes.
Description
- Company Type
- Established Company
- Working Model
- Hybrid, Onsite
- Industry
- Industry, Production
Senior AI Systems & Platform Engineer
- Location
- Dresden
- Working Model
- Onsite
- Diversity
- Open for all genders
- English Only
- English only required
