Senior AI Application Engineer: LLM/VLM on Edge

Axelera AI; Finland; Remote; EUR 90,000 - 150,000; Full time

Benefits offered by this job

Pension plan

Extensive insurances

Company shares

Job summary

Axelera AI is seeking a Senior AI Application Engineer to own LLM and VLM support on Metis and Europa AIPUs, from model study to shipping features in the Voyager SDK. The role blends AI inference expertise with practical software engineering, including working with AI coding agents on real codebases.

You will prototype, validate, and productize results, ensuring stable APIs, tests, and release gates, while collaborating with teams across Europe and remote environments.

Qualifications

• 5+ years in software engineering with ML inference experience.
• Deep understanding of transformer inference and KV caching.
• Strong Python and PyTorch, production-grade software shipping.
• Experience with AI coding agents and real codebases.

Responsibilities

• Study new LLM/VLM architectures and prototype on Metis and Europa.
• Productize results into Voyager SDK features with stable APIs.
• Own contracts for LLM/VLM blocks including inputs, outputs, weights, and state.
• Integrate LLM/VLM serving into the Voyager SDK pipeline.

Skills

Python

PyTorch

Transformer inference

ML systems

AI agents

Software engineering

Education

Bachelor's degree in CS

Tools

Triton

ONNX Runtime

vLLM

MLIR

Job description

Axelera AI is seeking a Senior AI Application Engineer to own LLM and VLM support on Metis and Europa AIPUs, from model study to shipping features in the Voyager SDK. The role blends AI inference expertise with practical software engineering, including working with AI coding agents on real codebases.

You will prototype, validate, and productize results, ensuring stable APIs, tests, and release gates, while collaborating with teams across Europe and remote environments.