GPU Software Engineer (Remote)

Role: GPU Software Engineer (Remote) Location: Remote (Work from Anywhere) Job Type: Contract Payout: $60 - $85/hour Role Overview: We are hiring for one of our clients, seeking a GPU Programming Software Engineer to work on a contract basis. The role involves developing high-performance computing solutions leveraging GPU architectures for computational workloads. You will optimize parallel processing frameworks and implement GPU-accelerated algorithms for large-scale data processing. Key Responsibilities: • Design and implement GPU-optimized software solutions for high-performance computing applications • Develop and maintain CUDA/OpenCL-based kernels and libraries for parallel computation • Profile and optimize existing codebases to improve GPU utilization and reduce latency • Collaborate with cross-functional teams to integrate GPU acceleration into existing workflows • Write unit tests and benchmarks to validate performance improvements and correctness Required Skills & Qualifications: • Proficiency in CUDA programming and GPU architecture optimization • Experience with OpenCL, HIP, or other GPU computing frameworks • Strong C/C++ programming skills with a focus on performance tuning • Familiarity with parallel algorithms and data structures • Knowledge of numerical computing libraries like cuBLAS, cuFFT, or Thrust More About the Opportunity: This role offers a unique opportunity to work with a global leader in the Technology, Information and Internet industry, contributing to the development of scalable GPU solutions for industry-specific computational challenges. The position requires independent problem-solving and the ability to deliver high-performance code in a fast-paced environment. Equal Opportunity Employer: We hire based on skills and expertise. All qualified candidates are welcome regardless of background, experience, or prior employment history. Applications are reviewed solely on demonstrated technical ability and qualifications. Apply Now!

Design and implement GPU-optimized software solutions and CUDA/OpenCL-based kernels for high-performance computing. Profile and optimize existing codebases to improve GPU utilization and reduce latency.

Requires proficiency in CUDA programming, GPU architecture optimization, and strong C/C++ skills. Experience with parallel algorithms and numerical computing libraries like cuBLAS or cuFFT is necessary.

• C++Preferred

Identified from the job description. Confirm important requirements above.

• Cuda
• Gpu Architecture Optimization
• Opencl
• Hip
• C++
• Performance Tuning
• Parallel Algorithms
• Data Structures
• Cublas
• Cufft
• Thrust

• Software
• Technology
• Engineering
• Science & Research
• Consulting

Minimum experience

2+ years

Posting language

English

Working hours

40 hours per week

Seniority

Associate