Introduction
We are seeking an Edge AI Systems Designer who specializes in creating AI architectures tailored for edge computing environments. If you are passionate about enabling AI on IoT devices, smartphones, autonomous systems, and embedded platforms, this role offers the opportunity to design the future of real-time, on-device intelligence.
As an Edge AI Systems Designer at our organization, you will optimize models for deployment in constrained environments, ensuring efficiency, scalability, and low-latency performance. You’ll collaborate with hardware, software, and ML teams to deliver AI capabilities where connectivity and computing power are limited.
We offer competitive compensation, comprehensive benefits, and opportunities to advance cutting-edge AI at the edge.
Objectives of this role
- Architect AI models optimized for edge deployment and resource efficiency.
- Collaborate with hardware teams to integrate AI on embedded and IoT devices.
- Ensure reliability and low latency in offline or bandwidth-limited environments.
- Research and apply emerging methods for edge AI optimization.
Your tasks
- Design workflows for deploying AI models on edge hardware.
- Implement techniques such as quantization, pruning, and compression.
- Test models on diverse devices to validate performance and reliability.
- Collaborate on real-time AI applications in robotics, IoT, and autonomous systems.
- Monitor performance metrics and continuously optimize edge solutions.
- Document and share best practices for edge AI deployment.
Required skills and qualifications
- Bachelor’s degree in Computer Engineering, Electrical Engineering, or Computer Science.
- Strong programming skills in Python, C++, and embedded systems.
- Experience with ML frameworks for edge (TensorFlow Lite, PyTorch Mobile, ONNX).
- Knowledge of hardware acceleration (GPU, TPU, FPGA, ASIC).
- Familiarity with IoT systems and distributed architectures.
Preferred skills and qualifications
- Advanced degree in Embedded AI, Robotics, or Systems Engineering.
- Experience deploying AI on microcontrollers and specialized edge devices.
- Knowledge of low-power optimization techniques.
- Contributions to edge AI open-source projects.
- Experience in safety-critical edge AI applications.
