High-Performance GPU Algorithms Engineer

ApplyMint; Odense; On-site; DKK 900,000 - 1,200,000; Full time

Benefits offered by this job

Competitive salary package

Pension

Standard employment benefits

Job summary

Qpurpose is seeking an Algorithmic Software Engineer focused on GPU programming and accelerated computing. You will design high-performance algorithms, implement kernels, and integrate GPU-accelerated modules within broader systems.

The role involves collaborating with Python/C++ components, profiling and tuning for modern hardware, and advancing projects toward potential quantum integration in the longer term.

Qualifications

• Bachelor's or Master's in Computer Science, Mathematics, Physics, Engineering, or a related field.
• Strong programming experience in GPU programming using CUDA, HIP, OpenCL or similar frameworks.
• Experience with performance profiling, memory optimization, parallel programming or HPC.

Responsibilities

• Design and implement high-performance algorithms for GPU and accelerated computing environments.
• Develop computational kernels, numerical methods, data pipelines, and backend systems for data-intensive applications.
• Optimize software for performance, scalability, memory usage, and reproducibility.
• Develop scalable solutions across domains such as ML, optimization, computational biology, finance, and logistics.
• Collaborate with Python and/or C++ components and integrate GPU-accelerated modules into larger systems.
• Benchmark, profile, and tune algorithms to run efficiently on modern hardware.
• Communicate assumptions, tradeoffs, and limitations to technical and non-technical stakeholders.

Skills

GPU programming

Performance profiling

Parallel programming

Ownership / initiative

Education

Bachelor's or Master's in CS/Math/Physics/Engineering

Tools

CUDA

HIP

OpenCL

Job description

Qpurpose is seeking an Algorithmic Software Engineer focused on GPU programming and accelerated computing. You will design high-performance algorithms, implement kernels, and integrate GPU-accelerated modules within broader systems.

The role involves collaborating with Python/C++ components, profiling and tuning for modern hardware, and advancing projects toward potential quantum integration in the longer term.