Senior AI Application Engineer — Remote GenAI & Edge

Axelera AI; Italia; Remote; EUR 120,000 - 150,000; Full time

Benefits offered by this job

Pension plan

Extensive employee insurances

Company shares

Job summary

Axelera AI is seeking a Senior AI Application Engineer for the Model Enablement team to own LLM and VLM support on Metis and Europa AIPUs, from model study to shipping features in the Voyager SDK. This role blends ML inference know-how with hands-on software engineering and daily use of AI coding agents on real codebases.

You will contribute to productization, define runtime contracts, and help steer GenAI direction for edge devices, with flexible remote options across Europe and potential

Qualifications

• 5+ years of software engineering experience, with ML inference exposure.
• Solid understanding of transformer inference: attention variants, KV caching, prefill vs Decode.
• Strong Python and PyTorch, and experience shipping production-quality software.
• Daily use of AI coding agents on real codebases with good judgment to verify output.

Responsibilities

• LLM/VLM study: study new LLM and VLM families and architectures and prototype on Metis/Europa.
• Productization: turn results into Voyager SDK features with stable APIs and tests.
• Model-side contracts: own PyTorch reference, weight mapping, and input/output contracts.
• Pipeline integration: bring LLM/VLM serving into Voyager SDK pipeline builder.
• Quality: measure accuracy vs floating-point reference and explain gaps.
• Bring-up platform: extend environments with compiler/runtime/hardware access for closed-loop tests.
• GenAI direction: advise Voyager SDK needs for GenAI and edge-dedicated demos.

Skills

Python

PyTorch

Transformer inference

ML tooling

AI coding agents

Software engineering

Tools

Triton

TVM

MLIR

ONNX Runtime GenAI

LLM/VLM tooling

Job description

Axelera AI is seeking a Senior AI Application Engineer for the Model Enablement team to own LLM and VLM support on Metis and Europa AIPUs, from model study to shipping features in the Voyager SDK. This role blends ML inference know-how with hands-on software engineering and daily use of AI coding agents on real codebases.

You will contribute to productization, define runtime contracts, and help steer GenAI direction for edge devices, with flexible remote options across Europe and potential