Senior HPC Scheduler & Grid Reliability Engineer

Qualcomm; Ciudad de México; Presencial; MXN 900.000 - 1.300.000; Jornada completa

Descripción de la vacante

Qualcomm is seeking a Senior HPC Scheduler Operations Engineer to operate, scale, and optimize the IBM Spectrum LSF-based scheduling stack for large-scale EDA workloads. You will work within Engineering IT Hardware Infrastructure — EDA Compute, influencing reliability and performance across sites.

Proven Linux administration, scripting skills, and strong problem-solving are required. Preference for Slurm exposure and container workload experience, with close collaboration to CAD/engineering

Formación

• Bachelor's degree in Computer Science, Electrical Engineering, or related field, or equivalent practical experience.
• 5+ years operating and supporting large-scale Linux-based compute infrastructure in HPC or silicon design environments.
• Strong hands-on experience with IBM Spectrum LSF, including queue configuration, policy tuning, fairshare, job arrays, and multi-cluster operations.
• Proficiency in SLES administration including OS-level troubleshooting, workload profiling and user environment management.
• Ability to independently analyze complex system behavior under load; experience with root cause analysis across scheduler, OS, and hardware layers.
• Proficiency in Python and/or Shell scripting for operational automation, data processing, and tooling development.
• Demonstrated ability to clearly articulate technical tradeoffs, reliability metrics, and operational status to both engineering and management audiences.

Responsabilidades

• Manage, scale, and optimize IBM Spectrum LSF job scheduling systems for EDA and HPC compute-intensive workloads across multi-site environments.
• Administer scheduler configuration including queue policies, resource limits, fairshare, job arrays, and preemption strategies.
• Analyze scheduler and infrastructure performance data to identify bottlenecks and improve utilization, throughput, and job turnaround time.
• Perform capacity planning and workload characterization to support SKU-level packing models and tiered job scheduling strategies.
• Implement and maintain scheduler tuning parameters to minimize dispatch latency and maximize grid efficiency under high-saturation conditions.
• Troubleshoot and resolve service-impacting issues across scheduler, OS, and workload layers with minimal time-to-resolution.
• Define and track SLOs for service performance and reliability; partner with customer teams to set and communicate realistic expectations.
• Implement automation and process improvements to reduce manual toil and prevent recurring incidents.
• Develop and enforce operational standards, runbooks, and best practices ensuring consistency across all sites.
• Build and maintain observability systems including metrics pipelines, dashboards, and alerting frameworks for scheduler and compute infrastructure health.
• Leverage accounting and telemetry data (e.g., LSF stream logs, bjobs, bacct) to quantify workload coverage, grid efficiency, and tier performance.
• Develop automation tooling (Python, Shell, APIs) to streamline operations, enforce policy guardrails, and surface actionable insights.
• Produce operational reports and management summaries that combine automated metrics with human operational narratives.
• Collaborate directly with CAD and engineering teams to clarify workload requirements, translate technical tradeoffs, and drive issues to closure.
• Communicate scheduler performance metrics, reliability posture, and capacity status clearly to engineering and management audiences.
• Partner with peer infrastructure teams to coordinate cross-functional changes and align on shared operational standards.

Conocimientos

LSF

Slurm

Linux

Python

Shell scripting

Problem solving

Communication

Educación

Bachelor's degree in CS/EE or related field

Herramientas

IBM Spectrum LSF

Slurm

Docker/Singularity

Descripción del empleo

Qualcomm is seeking a Senior HPC Scheduler Operations Engineer to operate, scale, and optimize the IBM Spectrum LSF-based scheduling stack for large-scale EDA workloads. You will work within Engineering IT Hardware Infrastructure — EDA Compute, influencing reliability and performance across sites.

Proven Linux administration, scripting skills, and strong problem-solving are required. Preference for Slurm exposure and container workload experience, with close collaboration to CAD/engineering