Senior AI Platform Engineer, LLM & VLM Enablement

Axelera AI; Netherlands; Hybrid; EUR 110,000 - 170,000; Full time

Benefits offered by this job

Pension plan

Extensive employee insurances

Stock options / company shares

Open and collaborative culture

Job summary

Axelera AI is seeking a Senior AI Application Engineer in the Model Enablement team to own LLM and VLM support on Metis and Europa AIPUs, from studying models to shipping them in Voyager SDK.

The role combines LLM/VLM knowledge with software engineering, using AI coding agents to build, test and verify your work, and collaborating with field engineers and leaders who value hands-on coding and practical design.

Qualifications

• 5+ years of software engineering experience, with at least 2 years on ML inference, ML systems or ML tooling.
• Transformer inference: attention variants, KV caching, prefill versus decode, sampling, tokenization, VLM alignment.
• Quantization for LLMs: weight-only and weight-activation schemes, calibration, outlier handling.
• Strong Python and PyTorch, shipping production-quality software.
• Daily use of AI coding agents on real codebases with good judgment.
• Turn research code and hardware constraints into a practical design.

Responsibilities

• LLM/VLM study: Study new LLM and VLM families and architectures, prototype and profile on Metis and Europa, and decide how they should run on our hardware.
• Productization: Turn results into Voyager SDK features with stable APIs, tests, docs and release gates.
• Model-side contracts: Own PyTorch reference with quantization, weight mapping, and a contract for inputs/outputs/weights, handed to compiler team.
• Pipeline integration: Bring LLM/VLM serving into Voyager SDK pipeline builder with KV-cache management and multimodal inputs.
• Quality: Measure accuracy vs reference and address gaps.
• LLM/VLM bring-up platform: Extend platform with environments, closed-loop runs, and evaluations against reference.
• GenAI direction: Recommend Voyager SDK needs for GenAI, agents and edge speech demos.

Skills

Software engineering

ML inference

Transformer inference

Python

PyTorch

AI coding agents

Quantization

Model validation

Production software

Tools

Triton

TVM

ONNX Runtime GenAI

Job description

Axelera AI is seeking a Senior AI Application Engineer in the Model Enablement team to own LLM and VLM support on Metis and Europa AIPUs, from studying models to shipping them in Voyager SDK.

The role combines LLM/VLM knowledge with software engineering, using AI coding agents to build, test and verify your work, and collaborating with field engineers and leaders who value hands-on coding and practical design.