HPC Architect

Responsibilities

• Serve as the technical architect for AbbVie IR's on-premises, cloud, and hybrid HPC based scientific-computing environments.
• Responsible for architecture, standards, infrastructure (software and hardware) lifecycle, evaluation of POC, capacity planning, and cost management.
• Architect and continuously evolve all aspects of scientific HPC computing platforms, including operational and maintenance processes.
• Design, implement, and support HPC compute and networking infrastructure - compute, networking, and storage.
• Administer and optimize Slurm workload management, including partitions, queues, priorities, fair-share, reservations, resource limits, GPU scheduling, accounting, job troubleshooting, performance tuning, and integration with Posit and other research platforms.
• Establish secure, reproducible container and scientific software environments using Apptainer/Singularity, Docker-compatible workflows, environment modules, compilers, MPI, CUDA, Python, R, and application dependencies.
• Assist with the architecture and support of Posit Workbench, Posit Connect, Posit Package Manager, and related analytics platforms, integrating them with Slurm, Active Directory, storage, GPUs, and scientific software.
• Implement secure identity and access management in accordance with AbbVie security SOPs and applicable industry standards.
• Architect, implement, and support vulnerability-management processes and remediation efforts.
• Lead efforts to automate provisioning, configuration, patching, testing, monitoring, remediation, and lifecycle activities.
• Maintain observability metrics, architecture diagrams, inventories, dependency maps, configuration standards, runbooks, support procedures, and end-of-life plans while addressing technical debt, operational risks, and capacity constraints.
• Lead the development of appropriate reporting and monitoring tools and dashboards.
• Lead design and incident reviews, vendor engagements, proofs of concept, capacity planning, and implementation governance; provide technical direction and mentorship to engineering and partner teams.
• Partner with R&D to create appropriate solutions for research workloads.

Qualifications

• Bachelor's Degree in Computer Science, IT, or related field with 7 years of experience; OR Master's Degree with 6 years of experience; OR PhD 2 years' experience.
• Respective years of experience in application program development.
• Leadership experience is required, including the ability to guide, collaborate with and influence technical teams, projects, and workstreams both within and outside the organizational structure.
• Demonstrated ability to balance technical depth with people leadership and stakeholder management.
• Expert knowledge of Linux, HPC compute and GPU architectures, CPU/memory/NUMA/PCIe design, MPI, NVIDIA GPUs, CUDA, MIG, node provisioning, firmware, drivers, and hardware lifecycle management.
• Strong experience with Slurm, including partitions, queues, scheduling policies, resource management, GPU scheduling, accounting, troubleshooting, and performance optimization.
• Strong knowledge of HPC networking, including Mellanox/NVIDIA InfiniBand, RDMA, Aruba switching, Ethernet, VLANs, routing, segmentation, subnet management, monitoring, and low-latency communications.
• Experience with high-performance and distributed storage, including Weka or comparable platforms, Lustre, NFS, CIFS/SMB, storage gateways, quotas, permissions, data movement, replication, backup, archival, and recovery.
• Experience integrating Active Directory or equivalent identity services with SSH, SSSD, sudo, service accounts, security groups, filesystem permissions, and least-privilege access models.
• Experience with Apptainer/Singularity, Docker-compatible workflows, container security, reproducibility, GPU/MPI enablement, image management, and scientific software environments using modules, compilers, Python, R, CUDA, and related dependencies.
• Experience supporting interactive research platforms such as Posit Workbench, Posit Connect, Jupyter, or comparable tools, including integration with Slurm, GPUs, identity services, storage, and software environments.
• Experience architecting cloud and hybrid HPC solutions, including networking, security, identity, provisioning, storage, autoscaling, infrastructure as code, workload placement, cost management, monitoring, and lifecycle operations.
• Strong scripting, automation, and DevOps skills.
• Knowledge of observability, centralized logging, alerting, incident response, root-cause analysis, capacity planning, performance engineering, cybersecurity, vulnerability management, encryption, patching, and access governance.
• Experience creating architecture diagrams, technical standards, operating models, runbooks, migration plans, lifecycle strategies, and executive-level recommendations.
• Experience working in Data Science, Life Sciences, or Pharmaceutical industry working in regulated or enterprise IT environments.

Preferred

Work experience in the pharmaceutical industry preferred.