Senior HPC Software Architect — Parallel Computing Lead

Cymertek Corporation; San Antonio (TX); On-site; USD 150,000 - 210,000; Full time

Benefits offered by this job

Excellent Salaries

Flexible Work Schedule

401k Matching

Paid Leave

Job summary

Cymertek Corporation is seeking an experienced HPC Software Architect in San Antonio, TX to lead the design of high-performance software for advanced computing systems. You will guide development teams, optimize applications for HPC environments, and ensure scalable, robust solutions across distributed platforms.

The role requires deep expertise in MPI/OpenMP, HPC architectures, and performance profiling, with experience in CUDA/TensorFlow and cloud readiness.

Qualifications

• Proven experience in designing high-performance software architectures for HPC.
• Strong knowledge of parallel programming models and HPC workflows.
• Experience with distributed systems and data-intensive computing.
• Proficiency in performance profiling and system-level optimization.
• Familiarity with HPC development tools and libraries like CUDA and TF.
• Ability to design fault-tolerant and scalable solutions.

Responsibilities

• Design and define high-performance software architectures
• Develop strategies for optimizing application performance on HPC systems
• Lead the integration of software with HPC infrastructure
• Collaborate with stakeholders to define technical requirements
• Ensure scalability and compatibility of HPC applications
• Oversee the development and deployment of HPC software solutions

Skills

MPI/OpenMP

HPC architectures

Distributed systems

Performance profiling

CUDA/TensorFlow

Fault-tolerant design

Education

Bachelor's Degree

Tools

CUDA

TensorFlow

Singularity

Job description

Cymertek Corporation is seeking an experienced HPC Software Architect in San Antonio, TX to lead the design of high-performance software for advanced computing systems. You will guide development teams, optimize applications for HPC environments, and ensure scalable, robust solutions across distributed platforms.

The role requires deep expertise in MPI/OpenMP, HPC architectures, and performance profiling, with experience in CUDA/TensorFlow and cloud readiness.