Senior AI Application Engineer – GenAI & Edge Inference

Axelera AI; España; Remote; EUR 110,000 - 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 to own LLM and VLM support across Metis and Europa AIPUs, from model study to shipping features in the Voyager SDK. The role blends deep ML inference with practical software engineering, using AI coding agents daily to build, test, and verify work.

You will push model enablement, quantization, and runtime integration while mentoring teams and shaping GenAI direction for edge devices. Flexible European remote options are available.

Qualifications

• 5+ years of software engineering experience with ML inference/systems or tooling.
• Solid understanding of transformer inference: attention variants, KV caching, prefill vs decode, sampling, tokenization.
• Knowledge of LLM quantization and how to detect quantization loss.
• Strong Python and PyTorch; production-quality software.
• Experience using AI coding agents on real codebases and evaluating outputs.

Responsibilities

• Study new LLM/VLM families and architectures; prototype and profile on Metis/Europa hardware.
• Turn research results into Voyager SDK features with stable APIs and tests.
• Own reference implementations and contracts for model building blocks; collaborate with compiler teams.
• Integrate LLM/VLM serving into Voyager SDK pipeline builder and KV-cache management.
• Measure accuracy against reference, explain gaps, and drive bring-up platform improvements.
• Define GenAI needs for Voyager SDK, agents, and edge-device demos.

Skills

Software engineering

ML inference

Transformer inference

Python

PyTorch

AI coding agents

Quantization

Tools

llama.cpp

vLLM

ONNX Runtime GenAI

ExecuTorch

Tensor compiler

Job description

Axelera AI is seeking a Senior AI Application Engineer to own LLM and VLM support across Metis and Europa AIPUs, from model study to shipping features in the Voyager SDK. The role blends deep ML inference with practical software engineering, using AI coding agents daily to build, test, and verify work.

You will push model enablement, quantization, and runtime integration while mentoring teams and shaping GenAI direction for edge devices. Flexible European remote options are available.