Staff AI Application Engineer (AI)

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

Company

hirify.global is a deep-tech company building the Metis AI Platform and next-generation AI solutions.

What you will do

• Build the model enablement platform and agent harness for partitioning, compiling, running, profiling, and verifying models on real hardware.
• Own model ingestion and determine how PyTorch and ONNX models are captured, analyzed, and split across AIPU matrix and RISC-V vector units, host CPUs, GPUs, NPUs, and video decoders.
• Extend heterogeneous execution to large models, cascades, and multi-model pipelines, including expert offloading and caching across device and host memory.
• Optimize end-to-end performance through host/device overlap, zero-copy buffers, batching, multi-core scheduling, and support for models with multiple inputs.
• Profile device time, host time, and data movement, and validate improvements in complete application pipelines with the graph compiler, runtime, and application teams.
• Study customer-critical models on Metis and Europa and turn findings into platform improvements.

Requirements

• 8+ years of engineering experience in systems, compilers, runtimes, or performance, including system-level design ownership.
• Hands-on experience with heterogeneous computing across CPU, GPU, DSP, NPU, or FPGA, including compute, memory bandwidth, latency, and data-movement analysis.
• Strong fundamentals in computer architecture, operating systems, and parallel programming.
• Familiarity with ML graph representations and compiler concepts, including graph capture with torch.export, FX, or ONNX, lowering, operator fusion, partitioning, and memory planning.
• Strong C++ and Python skills.
• Daily use of AI coding agents for real engineering work, with the judgment to review and test their output.

Nice to have

• Hands-on experience with MLIR or another compiler framework such as TVM, XLA, TorchInductor, or IREE.
• Experience with an inference runtime or execution engine, including ONNX Runtime execution providers or custom NPU and DSP runtimes.
• Experience with GPU compute using CUDA, OpenCL, or Vulkan, or SIMD optimization on Arm or x86.
• Experience with large-model execution techniques such as offloading, expert caching, speculative decoding, or pipelining across devices.
• Experience building agent environments, evaluation harnesses, verification frameworks, differential testing, regression detection, or MCP-based tooling.

Culture & Benefits

• Flexible remote, hybrid, and onsite working arrangements across Europe and the UK.
• Pension plan and extensive employee insurance.
• Option to receive company shares.
• Open, collaborative culture supporting creativity, continual innovation, ownership, and freedom with responsibility.
• Inclusive equal-opportunity environment.