Senior AI Application Engineer - LLM/VLM & Voyager SDK

Axelera AI; Polska; Remote; PLN 180,000 - 260,000; 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 on Metis and Europa AIPUs, from model study to shipping features in the Voyager SDK. The role blends AI/ML knowledge with solid software engineering, using AI coding agents daily to build, test, and verify work.

The position welcomes hands-on engineers, tech leads, and managers returning to hands-on work, with experience planning, delegating, and reviewing transfers to AI agents.

Qualifications

• 5+ years of software engineering experience with ML tooling or ML inference.
• Solid understanding of transformer inference, attention and KV caching.
• Experience shipping production-quality software in Python and PyTorch.
• Daily use of AI coding agents on real codebases.
• Ability to translate research code and hardware constraints into practical design.

Responsibilities

• Study new LLM/VLM families and profiles for Metis and Europa. Prototype on hardware.
• Productize results into Voyager SDK features with stable APIs and tests.
• Define contracts for LLM/VLM blocks including input/output, weights and state.
• Integrate LLM/VLM into the Voyager SDK pipeline with KV-cache and decoding.
• Collaborate with quantization owners to measure accuracy vs reference.
• Extend the model enablement platform for bring-up on hardware with MCP tools.
• Recommend GenAI direction for Voyager SDK, edge agents and demos.

Skills

Software engineering

ML inference

Transformer inference

Python

PyTorch

AI coding agents

Tools

llama.cpp

vLLM

ONNX Runtime GenAI

ExecuTorch

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/ML knowledge with solid software engineering, using AI coding agents daily to build, test, and verify work.

The position welcomes hands-on engineers, tech leads, and managers returning to hands-on work, with experience planning, delegating, and reviewing transfers to AI agents.