Job Details

About the Company: A gpu and ai computing company seeking expertise in the technical and application areas described in this position. The role offers a focused setting for translating specialist knowledge into research, engineering or organizational outcomes.

Target Candidates: Master’s or PhD in Computer Science, Electronics, AI, HPC, Software, Applied Mathematics or a scientific-computing field.

Responsibilities

•  Optimize AI/HPC performance across instructions, drivers, compilers, math libraries, algorithms and frameworks.

•  Target large-model training/inference, scientific computing, physics, computational chemistry, bioinformatics and finite elements.

•  Explore processor architectures, programming models, compilers and parallel methods; develop kernels and inference/training integrations.

•  Coordinate multi-GPU/multi-node deployment with hardware, drivers, compiler and customer-solution teams.

•  The position translates practical operating needs into implementable technical plans, then follows the solution through development, integration and use. Attention to documentation, maintainability and feedback from application teams is part of the delivery scope.

Requirements

•  Master’s or PhD in Computer Science, Electronics, AI, HPC, Software, Applied Mathematics or a scientific-computing field.

•  GPU architecture, parallel programming, performance optimization, compilers, math libraries or AI frameworks.

•  C/C++ and Python; CUDA, OpenCL, Vulkan, Triton, TVM or MLIR and distributed/large-model optimization preferred.

•  Candidates should connect system-level decisions with user needs, evaluate implementation trade-offs and coordinate clearly with engineering, operations or research stakeholders.

Highlights & Support: Core software-stack development for AI models, HPC and scientific computing on GPU platforms.