Staff AI Application Engineer - Heterogeneous Computing

About the role

Axelera AI is hiring a Staff AI Application Engineer in its Model Enablement team (Application Software). You will build the model enablement platform and decide how each model runs across the Metis or Europa AIPU, the host CPU and the host's accelerators. The work spans architecture and hands-on development across the model frontend, the graph compiler, the runtime and the application pipeline. The team uses AI coding agents in daily work, and the role welcomes experienced field application engineers, technical leads and engineering managers.

Key responsibilities

• Build the platform that engineers and AI agents use to bring up models: reusable tools to partition, compile, run and profile, environments with access to real hardware, closed-loop runs and verification integrated into CI.
• Own how a PyTorch or ONNX model is captured, analysed and split across the AIPU's matrix and RISC-V vector units, the host CPU and the host's accelerators (GPU, NPU, video decoder).
• Extend the split to large models, cascades and multi-model pipelines, with expert offloading and caching across device and host memory.
• With the application and runtime teams, optimise end-to-end performance: overlap of host and device work, zero-copy buffers, batching, multi-core scheduling, and profiling of device time, host time and data movement.
• Study the models that matter most to customers and turn lessons into platform improvements.

Required profile

• 8+ years of engineering experience in systems, compilers, runtimes or performance, including system-level design ownership.
• Hands-on experience with heterogeneous computing across CPU, GPU, DSP, NPU or FPGA, including compute, memory bandwidth, latency and data movement.
• Solid fundamentals in computer architecture, operating systems and parallel programming.
• Familiarity with ML graph representations and compiler concepts: graph capture (torch.export, FX, ONNX), lowering, operator fusion, partitioning, memory planning.
• Strong C++ and Python, and daily use of AI coding agents with the judgment to review and test their output.

Preferred skills

• MLIR or another compiler framework (TVM, XLA, TorchInductor, IREE)
• Inference runtime or execution engine (ONNX Runtime execution providers, custom NPU or DSP runtime)
• GPU compute (CUDA, OpenCL, Vulkan) or SIMD optimization on Arm or x86
• Large-model techniques such as offloading, expert caching, speculative decoding and pipelining across devices
• Agent environments, evaluation harnesses or verification frameworks, or MCP-based tooling

What we offer

• Flexible working: office in Leuven, Amsterdam, Eindhoven, Zurich, Florence, Milan or Bristol, or fully remote from any European country, or relocation to Italy or the Netherlands.
• Compensation package including a pension plan, extensive employee insurance and the option to receive company shares.