Encharge AI
AI Runtime Engineer
U.S., Canada, Germany, Norway +4 · Remote · Full-time · Posted Jul 10, 2025
- Location
- U.S., Canada, Germany, Norway
Canada
Germany
Norway
Remote - US - Experience
- 3+ years developing low-level runtime software for AI accelerators, GPUs, or HPC systems.
- Education
- Bachelor’s or Master’s degree in Computer Science, Electrical Engineering, or a related field.
About the job
Develop and optimize low-latency runtime software for executing deep learning workloads on EnCharge AI accelerators across cloud and edge environments.
What you'll do
- Develop runtime components for task scheduling, memory management, kernel execution, and host-device data movement.
- Design high-performance APIs and optimize graph execution through kernel fusion, pipelining, tensor tiling, and caching.
- Integrate the runtime with AI frameworks and compilers, and improve reliability and scalability for cloud and edge deployments.
What they ask for
- 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; understanding of task scheduling, concurrency, and memory hierarchy.
- Experience with hardware-aware optimizations and dataflow architectures.
Nice to have
- Familiarity with deep learning execution frameworks such as ONNX Runtime, TensorRT, TVM, or OpenVINO.
- Exposure to AI model deployment pipelines such as Triton or TensorFlow Serving.
Tools
C/C++, PCIe, DMA, OpenVino, ONNX Runtime, vLLM, LLVM, MLIR
AI focus
Develop runtime software and optimize inference and training execution for deep learning models on specialized AI accelerator hardware.
Model-written summary · the original posting is authoritative