Performance Kernel Engineer for AI Accelerators

Arago Inc.; Paris; On-site; EUR 90,000 - 140,000; Full time

Benefits offered by this job

Stock options

Relocation bonus

Healthcare coverage

Pension contributions

25 days PTO

Professional development support

Transport reimbursement

Job summary

Arago is an AI and hardware company building software running on its custom AI accelerators. As a Performance Software Engineer, you will bridge host systems and hardware, from on-board kernels to real-time debugging, and contribute to chip bring-up and high-performance kernels.

You will use C/C++, assembly, and architecture-specific intrinsics on RISC-V and ARM, read hardware specs, and optimize for latency and throughput while collaborating with hardware and RTL teams.

Qualifications

• Bachelor's, Master's, or PhD in Computer Science, Computer Engineering, or a related field.
• Strong experience in low-level systems programming using C/C++ and assembly with understanding of compiled software maps to hardware.
• Bare-metal development including startup code, linker scripts, memory layout, MMIO, interrupts/exceptions, timers, synchronization, and peripheral access.
• Solid knowledge of computer architecture (pipelines, caches, memory hierarchies, DMA, addressing).
• Hands-on experience with RISC-V and/or ARM architectures, intrinsics, ABI concepts.
• Experience debugging hardware/software interactions using GDB, JTAG, trace interfaces, simulators, emulators, or FPGA.
• Ability to read hardware specifications and RTL docs and translate to robust software.
• Strong performance-analysis and optimization skills, including profiling and hand-tuned assembly where appropriate.
• Language: English proficient; French is a plus.

Responsibilities

• Develop and optimize low-level software primitives in C/C++, assembly, and architecture-specific intrinsics for RISC-V and ARM.
• Implement performance-critical kernels, runtime components, HALs, drivers, and firmware in bare-metal environments.
• Collaborate with hardware architects to define memory maps, register interfaces, interrupts, and boot flows.
• Analyze and optimize software for latency, throughput, memory footprint, and processor/accelerator utilization.
• Bring up and debug software on simulation, emulation, FPGA, and silicon platforms; address HW/SW integration issues.
• Develop validation tests, benchmarks, and diagnostic tools for processor, DSP, accelerator, and SoC functionality.
• Contribute to ISA extensions, compiler intrinsics, memory hierarchy, DMA, and cache/coherency decisions.

Skills

C/C++ development

Assembly language

Bare-metal programming

Computer architecture

RISC-V/ARM

Debugging tools

Low-level debugging

English proficiency

Education

CS/CE degree

Tools

GDB

JTAG

Trace tools

Job description

Arago is an AI and hardware company building software running on its custom AI accelerators. As a Performance Software Engineer, you will bridge host systems and hardware, from on-board kernels to real-time debugging, and contribute to chip bring-up and high-performance kernels.

You will use C/C++, assembly, and architecture-specific intrinsics on RISC-V and ARM, read hardware specs, and optimize for latency and throughput while collaborating with hardware and RTL teams.