Grid Operations Architect

Job Family: Software

Req : 519567

We are a leading global software company dedicated to the world of computer aided design, 3D modeling and simulation— helping innovative global manufacturers design better products, faster! With the resources of a large company, and the energy of a software start-up, we have fun together while creating a world class software portfolio. Our culture encourages creativity, welcomes fresh thinking, and focuses on growth, so our people, our business, and our customers can achieve their full potential.

Position Overview:

Siemens DISW’s Engineering Grid Computing Services team strategically supports over 3000 engineers located in R&D centers worldwide. The Engineering Grid Computing Service (EGCS) within GTI operates 18+ globally distributed high-performance computing grids across 7+ sites, currently provisioning 263,000+ CPU cores across four scheduler platforms (Altair Grid Engine, Altair Accelerator, IBM LSF, and SLURM). This infrastructure processes up to 12 million jobs per day at peak and serves approximately 3,000 engineers — it is the compute backbone that chip design, verification, and validation depend on.

We are seeking a Grid Operations Architect to own the architectural vision and technical strategy for the next generation of this computing fabric. The immediate mandate: scale consolidated grid capacity from a quarter million cores to almost one million cores over the next five-six years while simultaneously transforming and modernizing the entire environment— the migration from Altair Grid Engine to Accelerator Plus, a hierarchical scheduler purpose-built for the throughput demands of EDA workloads This is a senior technical leadership role that bridges grid operations, infrastructure engineering, and strategic planning.

Today, a lean team of 3 core grid administrators and 4 regional service delivery partners operate this global service — the Architect role is the structural investment that accelerates transformation and reduces key-person risk. You will define how Siemens DISW’s compute infrastructure is designed, deployed, and operated on a world-class scale. The key purposes of this role are based on the following:

• As EDA workloads grow and push the limits of what performance can be achieved with existing designs, a next generation architecture is the answer to meet the growing computing demands.

• The Accelerator migration is the architectural response — and it needs a dedicated owner.

• Key Technical/Strategic leadership need has been identified, providing depth and resilience to team

• The path to 24x5 follow-the-sun coverage, >50% toil reduction through automation, and full-service excellence depends on an architectural foundation that today's operational team does not have the bandwidth to design.

Key Responsibilities:

• Own the multiyear architectural roadmap for scaling grid compute capacity from 263K+ cores to 1M+ cores across 18+ globally distributed grids, consolidating across sites while maintaining availability and performance.

• Design the phased migration plan from AGE to Accelerator's hierarchical scheduling platform

• Design next generation grid topologies, scheduling frameworks, and resource management strategies that optimize utilization, throughput, and cost efficiency at a million core scale. One of the largest grids alone handles 60K+ cores and 2M+ jobs/dayarchitectures must perform at this density.

• Develop consolidation strategies to reduce operational complexity rationalizing 4 scheduler platforms toward a unified Accelerator based model, standardizing tooling, and harmonizing operational policies across regions.

• Lead capacity planning and forecasting models that project compute demand growth using linear, exponential, and flat percentage projections. Translate business requirements into infrastructure investment plans aligned with the 80% utilization ceiling and 72% procurement trigger governance model.

• Architect hybrid and cloud burst strategies (e.g., Nav Ops ) to augment on premises capacity for peak demand and elastic workloads working with A&S and Networking teams while respecting the latency and data locality requirements of EDA workloads

• Desig…