Senior AI Application Engineer - LLM & VLM Enablement

About the role

Axelera AI is hiring a Senior AI Application Engineer in its Model Enablement team (Application Software). You will own LLM and VLM support on Metis and Europa AIPUs, from studying new models to shipping them in the Voyager SDK. The role combines LLM/VLM knowledge with solid software engineering, and the team uses AI coding agents in daily work.

Key responsibilities

• Study new LLM and VLM families and architectures (e.g. mixture-of-experts, small VLMs, new attention and decoding schemes), prototype and profile them on Metis and Europa, and decide how they run on the hardware.
• Turn results into supported Voyager SDK features with stable APIs, tests, documentation and release gates.
• Own the PyTorch reference, weight mapping and a contract listing inputs, outputs, weights and persistent state (e.g. paged KV cache) for each building block, and hand it to the compiler team.
• Integrate LLM and VLM serving into the Voyager SDK pipeline builder: prefill and decode, KV-cache management, streaming text output and multimodal inputs.
• Measure accuracy against the floating-point reference with the regression and quantization owners, and close or explain each gap.
• Extend the model enablement platform with environments accessing the compiler, runtime and real hardware, closed-loop runs and evaluations.
• Recommend what the Voyager SDK needs for GenAI, agents and speech on edge devices.

Required profile

• 5+ years of software engineering experience, with at least 2 years on ML inference, ML systems or ML tooling.
• Solid understanding of transformer inference (attention variants, KV caching, prefill vs decode, sampling, tokenization, VLMs).
• Working knowledge of LLM quantization (weight-only and weight-activation schemes, calibration, outlier handling).
• Ability to turn research code and hardware constraints into a practical design.
• Preferred: experience with inference engines or serving stacks (llama.cpp, vLLM, ONNX Runtime GenAI, ExecuTorch), kernel development or tensor compilers (Triton, TVM, MLIR), speech (ASR, TTS) or agentic applications on embedded devices, and building evaluation or testing harnesses.

Required skills

• Strong Python and PyTorch
• Shipping production-quality software
• Daily use of AI coding agents on real codebases

What we offer

• Flexible working: office in Leuven, Amsterdam, Eindhoven, Zurich, Florence, Milan or Bristol, or fully remote from any European country; relocation to Italy or the Netherlands.
• Attractive compensation with a pension plan, extensive insurance and the option to get company shares.