AI Application Engineer

Location: Kodaira, Japan; onsite, with no remote work available

Company

hirify.global provides embedded semiconductor solutions for automotive, industrial, infrastructure, and IoT applications, with operations in more than 30 countries.

What you will do

• Enable and deploy BEV, object detection, segmentation, classification, and other AI models on automotive-grade Gen4/5 SoC platforms.
• Analyze latency, throughput, multi-core scaling, memory bandwidth, scheduling, and operator-mapping bottlenecks.
• Optimize inference workflows through post-training quantization, quantization-aware training collaboration, operator fusion, graph optimization, and execution partitioning.
• Integrate models into Linux and QNX embedded runtimes and debug NPU, DSP, CNNIP, memory, IPMMU, data-transfer, and synchronization issues.
• Validate AI workloads on target boards and SIL/HIL simulators while maintaining benchmarking and model-validation tools.
• Collaborate with compiler/runtime teams, customers, and field application engineers on evaluations, proofs of concept, demos, documentation, and release validation.

Requirements

• Bachelor’s or Master’s degree in Computer Science, Electrical Engineering, Embedded Systems, or equivalent embedded-systems experience.
• Solid understanding of deep learning fundamentals and inference pipelines.
• Hands-on experience with PyTorch, ONNX, or ONNX Runtime.
• Strong Python programming skills; working knowledge of C/C++ is beneficial.
• Familiarity with embedded systems, debugging tools, and performance metrics including latency, throughput, and hardware utilization.
• Ability to communicate effectively in a multicultural, cross-functional environment.

Nice to have

• 1–3 years of experience in embedded systems or AI-related development.
• Experience with computer vision, automotive or robotics use cases, and AI inference optimization on embedded hardware.
• Knowledge of INT8 quantization, calibration methods, QDQ ONNX models, memory hierarchy, DMA, and multi-core scheduling.
• Experience with automotive SoCs, safety-related software, QNX, ADAS perception pipelines, or automotive AI standards.
• Customer support, application engineering, internal tooling, documentation, or ONNX graph debugging experience.

Culture & Benefits

• Work within a transparent, agile, global, innovative, and entrepreneurial culture.
• Collaborate with more than 21,000 engineers and problem-solving professionals worldwide.
• Competitive compensation and comprehensive benefits are provided.
• Detailed benefits information is shared during the selection process.