AI Runtime Engineer

Location: United States, Canada, Germany, or Norway

Company

hirify.global develops advanced AI hardware and software systems for efficient edge-to-cloud computing, using in-memory computing technology for power-, energy-, and space-constrained applications.

What you will do

• Develop and optimize the runtime software stack for executing deep learning workloads on specialized AI accelerators.
• Implement task scheduling, memory management, kernel execution, and data-movement strategies using PCIe, DMA, and shared memory.
• Design high-performance APIs for OpenVINO, ONNX Runtime, and vLLM inference frameworks.
• Optimize graph execution through kernel fusion, pipelining, tensor tiling, and caching.
• Integrate runtime components with LLVM, MLIR, XLA, and TVM compilers.
• Improve scalability and reliability for cloud-based and edge AI deployments.

Requirements

• Bachelor’s or Master’s degree in Computer Science, Electrical Engineering, or a related field.
• 3+ years of experience developing low-level runtime software for AI accelerators, GPUs, or HPC systems.
• Strong proficiency in C/C++ and low-level systems programming.
• Deep understanding of task scheduling, concurrency, memory hierarchy, hardware-aware optimization, and dataflow architectures.
• Experience with deep learning execution frameworks such as ONNX Runtime, TensorRT, TVM, or OpenVINO.
• Strong debugging and profiling skills, with experience optimizing low-latency, high-throughput AI workloads.

Nice to have

• Exposure to AI model deployment pipelines such as Triton or TensorFlow Serving.

Culture & Benefits

• Work at the intersection of semiconductor design, AI systems, hardware, compilers, and AI frameworks.
• Collaborate across hardware, compiler, and AI framework teams.
• Build technology for both cloud and edge computing environments.
• Join a company launched in 2022 and led by experienced technologists in semiconductor design and AI systems.