Staff AI Platform Engineer, Heterogeneous Compute

Axelera AI; Zürich; Hybrid; CHF 150,000 - 210,000; Full time

Benefits offered by this job

pension plan

extensive employee insurances

the option to get company shares

Job summary

Axelera AI is seeking a Staff AI Application Engineer to help build our model enablement platform and optimize end-to-end performance across Metis/Europa AIPU, host CPU and accelerators. You will balance frontend, graph compiler and runtime work, with a device-side focus on backend concerns.

You will work with AI coding agents, participate in planning and code reviews, and contribute to scalable, differential testing and verification across the pipeline.

Qualifications

• 8+ years of engineering experience in systems, compilers, runtimes or performance.
• Hands-on experience with heterogeneous computing across CPU, GPU, DSP, NPU or FPGA.
• 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.
• Daily use of AI coding agents on real engineering work, with the judgment to review and test their output.

Responsibilities

• Model enablement platform and agent harness: Build the platform that engineers and AI agents use to bring up models; provide tools to partition, compile, run and profile; ensure access to real hardware; implement closed-loop verification integrated into CI.
• Model ingestion: Capture, analyze and split PyTorch/ONNX models across AIPU units, CPU and accelerators with placement tags read/overridden by users.
• Heterogeneous execution: Extend splits to large models and multi-model pipelines with caching and expert offloading.
• End-to-end performance: Coordinate with pipeline and runtime teams to optimize host-device overlap, zero-copy buffers, batching and scheduling.
• Critical models: Study models important to customers and translate lessons into platform improvements.

Skills

Systems engineering

Heterogeneous computing

Computer architecture

ML graph concepts

C++

Python

AI coding agents

Tools

PyTorch

ONNX

Job description

Axelera AI is seeking a Staff AI Application Engineer to help build our model enablement platform and optimize end-to-end performance across Metis/Europa AIPU, host CPU and accelerators. You will balance frontend, graph compiler and runtime work, with a device-side focus on backend concerns.

You will work with AI coding agents, participate in planning and code reviews, and contribute to scalable, differential testing and verification across the pipeline.