Software Engineer-Runtime

Company:** Kinara Inc. USA

Job Summary

Kinara Inc. USA is seeking a talented and motivated Software Engineer to join our Runtime team. In this role, you will be instrumental in designing, developing, and optimizing the core runtime software that powers our cutting-edge AI accelerators. You will contribute to creating efficient, high-performance, and robust solutions for deploying and executing AI models.

Responsibilities

• Design, implement, and optimize runtime software components for Kinara's AI accelerator hardware.
• Develop and maintain low-level software that interfaces with hardware, including drivers, firmware, and embedded software.
• Optimize runtime performance for various AI workloads, focusing on latency, throughput, and memory utilization.
• Collaborate with hardware design engineers to define and refine hardware-software interfaces.
• Work closely with AI framework teams to integrate and support popular AI models and operators.
• Debug and troubleshoot complex software and hardware interactions.
• Write clear, concise, and well-documented code, along with unit and integration tests.
• Participate in code reviews to ensure code quality, maintainability, and adherence to best practices.
• Research and evaluate new technologies and techniques to improve runtime efficiency and capabilities.
  
  

• Bachelor's or Master's degree in Computer Science, Electrical Engineering, or a related field.
• 2+ years of professional experience in software development, with a focus on systems programming or embedded systems.
• Proficiency in C/C++ programming and strong debugging skills.
• Experience with low-level programming and understanding of computer architecture.
• Familiarity with operating system concepts (e.g., memory management, scheduling, multithreading).
• Experience with performance profiling and optimization techniques.
• Excellent problem-solving skills and attention to detail.
• Ability to work effectively in a collaborative team environment.
• Strong communication skills, both written and verbal.
  
  

• Experience with AI accelerator runtime development.
• Familiarity with AI/ML frameworks (e.g., TensorFlow, PyTorch, ONNX Runtime).
• Knowledge of parallel computing and GPGPU programming (e.g., CUDA, OpenCL).
• Experience with embedded Linux or RTOS development.
• Understanding of compiler concepts and code generation.