Staff AI App Engineer - Heterogeneous Compute (Remote)

Axelera AI; Italia; Remote; EUR 90,000 - 140,000; Full time

Benefits offered by this job

Pension plan

Extensive employee insurances

Option to get company shares

Job summary

Axelera AI is seeking a Staff AI Application Engineer to build the model enablement platform that orchestrates model execution across Metis/Europa AIPUs, host CPUs and accelerators. You’ll shape the frontend, graph compiler, runtime and application pipeline while collaborating with a team that uses AI coding agents daily.

The role spans architecture and hands-on work with model bring-up, device-side backends, and performance optimization.

Qualifications

• 8+ years of engineering experience in systems, compilers, runtimes or performance with system-level design ownership.
• Hands-on experience with heterogeneous computing across CPU, GPU, DSP, NPU or FPGA and data movement considerations.
• Strong 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.
• Daily use of AI coding agents on real engineering work, with judgement to review and test their output.

Responsibilities

• Build the model enablement platform and agent harness for bringing up models across AIPU, host CPU and accelerators.
• Own ingestion of PyTorch/ONNX models with graph partitioning and placement tags for devices and hosts.
• Extend heterogeneous execution to large models and multi-model pipelines with expert offloading and caching.
• Collaborate with graph compiler and runtime teams to optimize end-to-end performance (overlaps, zero-copy, batching, scheduling).
• Study priority models and turn findings into platform improvements.

Skills

C++

Python

Heterogeneous computing

System-level design

AI coding agents

Tools

PyTorch

ONNX

Job description

Axelera AI is seeking a Staff AI Application Engineer to build the model enablement platform that orchestrates model execution across Metis/Europa AIPUs, host CPUs and accelerators. You’ll shape the frontend, graph compiler, runtime and application pipeline while collaborating with a team that uses AI coding agents daily.

The role spans architecture and hands-on work with model bring-up, device-side backends, and performance optimization.