Overview
In this role you will develop software that enables AI applications on next-generation accelerator hardware, bridging software, AI, and hardware teams. You will optimize low-level code, handle highly parallel data processing, and contribute to software frameworks that scale with hardware evolution. You’ll collaborate with hardware and AI teams to influence both software and future hardware direction, tackling performance-critical challenges. This position offers a chance to shape the software stack for high-performance AI workloads in a fast-growing, hardware-focused environment.
Responsabilidades
Work at the intersection of software, AI and hardware across optimisation, parallel data processing, workload analysis and frameworks.




Collaborate with hardware and AI teams to shape both software stack and hardware development.
Contribute to low-level optimisation and performance-enhancing efforts.
Support and refine software tooling that enables deployment of AI workloads on accelerator hardware.
Requisitos principales
Strong C/C++ and Python development experience
Working knowledge of RTOS
Embedded Linux knowledge is advantageous
Hands-on experience with software profiling and performance optimisation
Experience with C/C++ and Python interoperability, RISC-V / RISC-V Vector, architecture-based optimisation or CUDA/ROCm
C/C++
Python
RTOS
Embedded Linux
software profiling
CUDA

📌 Software-ontwikkelaar (Barcelona)
🏢 Jobrapido
📍 Barcelona