Staff AI Application Engineer — Heterogeneous Compute

Axelera AI; Amsterdam; Hybrid; EUR 140,000 - 190,000; Full time

Benefits offered by this job

Pension plan

Extensive employee insurances

Company shares

Job summary

Axelera AI is seeking a Staff AI Application Engineer - Heterogeneous Computing to build the model enablement platform and optimize execution across Metis, Europa AIPU, host CPU and accelerators. You will work across the frontend, graph compiler, runtime and pipeline, with coverage of both model bring-up and device-side execution.

The role blends architecture with hands-on engineering and welcomes experienced field application engineers, tech leads and managers who want to remain hands-on.

Qualifications

• 8+ years of engineering experience in systems, compilers, runtimes or performance with ownership.
• Familiarity with ML graph representations and compiler concepts: graph capture (torch.export, FX, ONNX), lowering, operator fusion, partitioning.
• Strong C++ and Python.
• Daily use of AI coding agents on real engineering work, with the judgment to review and test their output.
• Preferred: MLIR or another compiler framework (TVM, XLA, TorchInductor, IREE).
• Preferred: Inference runtime or execution engine (ONNX Runtime providers, custom NPU/DSP runtime).
• Preferred: GPU compute (CUDA, OpenCL, Vulkan) or SIMD on Arm/x86.

Responsibilities

• Model enablement platform and agent harness: Build a platform for partitioning, compiling, running and profiling models with real hardware access.
• Model ingestion: Capture, analyse and split models across AIPU units, host CPU and accelerators with readable tags.
• Heterogeneous execution: Extend splits to large models and multi-model pipelines with caching and offloading.
• End-to-end performance: Collaborate to maximize pipeline speedups with overlapped work and zero-copy buffers.
• Critical models: Study key models and translate lessons into platform improvements.

Skills

C++

Python

Heterogeneous compute

Graph representations

Linux

CI/CD

Tools

ONNX Runtime

CUDA

OpenCL

Job description

Axelera AI is seeking a Staff AI Application Engineer - Heterogeneous Computing to build the model enablement platform and optimize execution across Metis, Europa AIPU, host CPU and accelerators. You will work across the frontend, graph compiler, runtime and pipeline, with coverage of both model bring-up and device-side execution.

The role blends architecture with hands-on engineering and welcomes experienced field application engineers, tech leads and managers who want to remain hands-on.