Staff AI Application Engineer - Heterogeneous Computing

Axelera AIEindhovenHybridFull-time1 week ago

Axelera AI is seeking a Staff AI Application Engineer to build the model enablement platform for their Metis and Europa AI processing units. The role involves heterogeneous computing across CPU, GPU, NPU and other accelerators, requiring strong C++ and Python skills and 8+ years of systems/compiler experience. The position is based in Eindhoven, Netherlands, with flexible remote options across Europe.

What you'll do

Build the model enablement platform and agent harness: reusable tools to partition, compile, run and profile; environments with access to real hardware; closed-loop runs; verification integrated into CI.
Own model ingestion: capture, analyse and split PyTorch or ONNX models across AIPU matrix and RISC-V vector units, host CPU and host accelerators, with placement tags.
Extend heterogeneous execution to large models, cascades and multi-model pipelines, e.g., expert offloading and caching across device and host memory.
Bring each model to its best end-to-end performance: overlap of host and device work, zero-copy buffers, batching, multi-core scheduling, and models with several inputs.
Study critical models on Metis and Europa and turn lessons into platform improvements.

What you need

Must-have

C++PythonHeterogeneous computingComputer architectureOperating systemsParallel programmingML graph representationsCompiler concepts

Nice-to-have

MLIRTVMXLATorchInductorIREEONNX RuntimeCUDAOpenCL

Soft skills

JudgmentCollaborationOwnershipCreativityInnovation

AISemiconductorHeterogeneous ComputingCompilersRuntimesPerformanceC++PythonStaff EngineerEindhoven

/What you'll do

/What you need

Must-have

Nice-to-have

Soft skills

What you'll do

What you need