Senior AI Application Engineer

Location: Remote from any European country, including the UK; hybrid or onsite options are available at offices in Leuven, Amsterdam, Eindhoven, Zurich, Florence, Milan, and Bristol. Relocation options are available to Florence, Milan, Amsterdam, or Eindhoven. Priority is given to candidates interested in being based in Belgium or Italy.

Company

hirify.global is a deep-tech AI company developing the Metis AI Platform and Europa AI processing units for efficient edge AI applications.

What you will do

• Study new LLM and VLM families and architectures, prototype and profile them on Metis and Europa, and determine how they should run on the hardware.
• Turn research results into supported Voyager SDK features with stable APIs, tests, documentation, and release gates.
• Own PyTorch references with quantization, weight mappings, and complete input, output, weight, and persistent-state contracts for LLM/VLM building blocks.
• Integrate LLM and VLM serving into the Voyager SDK pipeline builder, including prefill, decode, KV-cache management, streaming text output, and multimodal inputs.
• Measure accuracy against floating-point references, investigate quantization losses and implementation gaps, and maintain quality with regression and quantization owners.
• Extend the LLM/VLM bring-up platform and recommend Voyager SDK capabilities, model-zoo demos, and GenAI, agent, and speech solutions for edge devices.

Requirements

• 5+ years of software engineering experience, including at least 2 years in ML inference, ML systems, or ML tooling.
• Strong understanding of transformer inference, including attention variants, KV caching, prefill versus decode, sampling, tokenization, and VLM integration of vision encoders with language models.
• Working knowledge of LLM quantization, including weight-only and weight-activation schemes, calibration, outlier handling, and distinguishing quantization loss from implementation bugs.
• Strong Python and PyTorch skills with experience shipping production-quality software.
• Daily use of AI coding agents on real codebases, with sound judgment when verifying or rejecting generated output.
• Ability to turn research code and hardware constraints into a practical design.

Nice to have

• Experience with inference engines or serving stacks such as llama.cpp, vLLM, ONNX Runtime GenAI, or ExecuTorch.
• Experience with kernel development, tensor compilers such as Triton, TVM, or MLIR, or model profiling on accelerator hardware.
• Experience with speech technologies such as ASR or TTS, or agentic applications on embedded devices.
• Experience building evaluation or testing harnesses for ML systems or AI agents, or tool-calling agents such as MCP servers.

Culture & Benefits

• Flexible remote, hybrid, and onsite work arrangements across Europe and the UK.
• International organization with an open culture supporting creativity, collaboration, continual innovation, ownership, and freedom with responsibility.
• Attractive compensation package with a pension plan, extensive employee insurances, and an option to receive company shares.
• Inclusive equal-opportunity environment.