Lead HPC Systems Engineer (TS/SCI Eligible)

Institute for Defense Analyses; Princeton (NJ); On-site; USD 121,000 - 194,000; Full time

Job summary

The Institute for Defense Analyses in Princeton, NJ seeks a Lead Systems Engineer to lead HPC infrastructure initiatives, manage compute clusters, and ensure secure, high-performance IT services for national programs.

The role requires expert Linux/Unix and Windows administration, Lustre storage, Slurm/HTCondor, MPI/CUDA, InfiniBand/GigE networking, and DoD security compliance. TS/SCI eligibility is preferred.

Qualifications

• Bachelor of Science degree in Computer Science or equivalent experience in related field.
• Eight years minimum experience in Information Technology, including at least six in systems administration.
• Advanced expertise in design, administration, and support of Linux/Unix and/or Windows systems.
• Experience with HPC or large cluster computing (GPU-based), Lustre or Hadoop.
• Experience with Slurm or HTCondor; MPI and CUDA knowledge.
• Experience with InfiniBand and GigE networks; security/compliance in a DoD environment.
• Ability to work with little supervision; strong written and verbal communication.
• Willingness to work outside regular hours; TS/SCI clearance or ability to obtain.

Responsibilities

• Takes the primary role as project leader and designer of new IT technology initiatives.
• Develops test and integration plans for new systems and software.
• Provides operational support and maintenance for system functionality, security and performance.
• Ensures systems meet business and security requirements per directives and guidelines.
• Mentors junior staff and coordinates work assignments to maintain schedules.
• Prepares technical documentation including SOPs and processes.
• Maintains classified and unclassified systems for optimal performance and availability.
• Keeps abreast of industry trends and recommends improvements.
• Communicates issues to supervisors and responds to after-hours support.

Skills

Project leadership

Written and verbal communication

On-call support

Education

Bachelor of Science in Computer Science or related field

Tools

Linux/Unix administration

Windows administration

Lustre storage

Slurm

HTCondor

MPI

CUDA

InfiniBand/GigE

DoD compliance/security

Open Source software

Job description

The Institute for Defense Analyses in Princeton, NJ seeks a Lead Systems Engineer to lead HPC infrastructure initiatives, manage compute clusters, and ensure secure, high-performance IT services for national programs.

The role requires expert Linux/Unix and Windows administration, Lustre storage, Slurm/HTCondor, MPI/CUDA, InfiniBand/GigE networking, and DoD security compliance. TS/SCI eligibility is preferred.