Embedded AI Engineer

Embedded AI Engineer - Job Description Job Title Embedded AI Engineer Location [City/Remote/Hybrid] Employment Type Full-time / Contract Job Summary We are seeking an Embedded AI Engineer to design, develop, and deploy AI-powered applications on embedded systems and resource-constrained devices. The ideal candidate will have expertise in embedded software development, machine learning, deep learning, and hardware acceleration to build intelligent, real-time solutions for industries such as automotive, consumer electronics, healthcare, robotics, industrial automation, and IoT. Key Responsibilities Design, develop, and deploy AI/ML applications on embedded devices and microcontrollers. Integrate machine learning and deep learning models into embedded software and firmware. Optimize AI models for low-power, low-memory, and real-time inference using quantization, pruning, and compression techniques. Develop embedded software using C/C++, Python, and embedded programming frameworks. Deploy AI models using TensorFlow Lite, TensorFlow Lite Micro, ONNX Runtime, TensorRT, OpenVINO, or similar inference frameworks. Interface AI applications with sensors, cameras, microphones, actuators, and communication modules. Collaborate with hardware, firmware, AI, and software engineering teams to build end-to-end intelligent embedded systems. Develop and optimize drivers, middleware, and application software for AI-enabled devices. Benchmark system performance, memory usage, latency, and power consumption. Implement secure boot, firmware updates, and device security best practices. Perform debugging, testing, validation, and troubleshooting across hardware and software components. Document system architecture, software design, deployment procedures, and technical specifications. Stay current with advancements in embedded AI, TinyML, AI accelerators, and edge computing technologies. Required Qualifications Bachelor's or Master's degree in Computer Science, Electronics, Embedded Systems, Electrical Engineering, Artificial Intelligence, Robotics, or a related field. 3-8+ years of experience in embedded systems, firmware development, AI/ML, or related software engineering roles. Strong programming skills in C/C++ and Python. Experience developing software for embedded Linux or RTOS environments. Hands-on experience with machine learning and deep learning model deployment. Knowledge of hardware interfaces such as UART, SPI, I2C, CAN, GPIO, USB, and Ethernet. Experience working with ARM-based processors, microcontrollers, or embedded platforms. Understanding of software optimization, debugging, and performance profiling techniques. Preferred Qualifications Experience with NVIDIA Jetson, Raspberry Pi,

STM32

, ESP32, NXP, Qualcomm, Texas Instruments, Renesas, or similar embedded platforms. Knowledge of TinyML and AI deployment on microcontrollers. Experience with computer vision, speech recognition, sensor fusion, or robotics applications. Familiarity with FPGA or AI accelerator hardware is an advantage. Experience with OTA firmware updates and device fleet management. Relevant certifications in embedded systems, AI, cloud, or IoT technologies. Technical Skills C/C++ Python Embedded Linux RTOS (FreeRTOS, Zephyr, ThreadX) ARM Cortex Processors STM32

ESP32

TensorFlow Lite TensorFlow Lite Micro TensorFlow PyTorch ONNX Runtime TensorRT OpenVINO OpenCV CUDA TinyML Edge Impulse Computer Vision Deep Learning Machine Learning Model Quantization Model Pruning UART SPI I2C CAN GPIO MQTT Docker Git

CI/CD

REST APIs Soft Skills Analytical thinking Problem-solving Communication Collaboration Innovation Attention to detail Time management Adaptability Continuous learning Key Deliverables AI-enabled embedded software and firmware Optimized AI models for embedded deployment Real-time inference applications Hardware and software integration solutions Performance benchmarking and optimization reports Technical documentation Secure firmware deployment and update mechanisms System validation and testing reports Success Metrics AI model inference speed and accuracy Memory and power optimization System stability and reliability Successful deployment on target embedded hardware Reduction in latency and resource utilization Product quality and defect reduction Compliance with security, safety, and quality standards Timely delivery of embedded AI features and product releases Ova Technologies