We are seeking an Edge AI & Embedded ML Engineer to develop high-performance, low-latency AI models for deployment on resource-constrained devices. This role involves optimizing deep learning models for real-time inference on edge hardware, ensuring efficiency in power-limited environments.

If you have experience with TinyML, on-device AI, and embedded neural networks, this is the perfect opportunity to work on cutting-edge innovations.

Tasks

• Design, train, and optimize machine learning models for deployment on microcontrollers, FPGAs, TPUs, and custom ASICs
• Implement low-power deep learning solutions for edge devices
• Optimize models using quantization, pruning, knowledge distillation, and hardware-aware training
• Deploy and benchmark ML models on TensorFlow Lite, ONNX, PyTorch Mobile, and Edge TPU
• Develop firmware/software to integrate AI models with real-time operating systems (RTOS), IoT networks, and embedded Linux
• Collaborate with hardware engineers to improve AI performance on custom architectures

Requirements

• Experience in embedded software development for AI & TinyML applications
• Proficiency in C, C++, and Python for real-time, low-power systems
• Knowledge of microcontroller architectures and RTOS (Zephyr, FreeRTOS, etc.)
• Ability to work cross-functionally in a fast-moving, collaborative environment
• Passion for pushing the limits of Edge AI & embedded ML innovation

Benefits

🚀 Work on the bleeding edge of blockchain & AI innovation.
🌍 Remote-first team with a flexible work culture.
💡 Opportunity to shape the future of decentralized AI applications.
💰 Competitive salary & potential for equity/token incentives.

Join Avo Intelligence and revolutionize AI! Work with cutting-edge TinyML tech, collaborate globally, and make an impact. Apply now for the Embedded Software Engineer role!