Edge AI Engineer - Job Description (JD) Job Title Edge AI Engineer Job Summary We are seeking an experienced Edge AI Engineer to design, develop, optimize, and deploy Artificial Intelligence (AI) and Machine Learning (ML) models on edge devices. The ideal candidate should have expertise in embedded systems, computer vision, deep learning, model optimization, IoT, edge computing, and hardware acceleration. You will work on deploying AI solutions to devices such as cameras, drones, robots, automotive systems, industrial equipment, and IoT devices while ensuring low latency, high performance, and energy efficiency.

Key Responsibilities Design, develop, and deploy AI/ML models on edge devices. Optimize deep learning models for resource-constrained hardware. Develop computer vision and real-time inference applications. Convert and optimize models using TensorFlow Lite, ONNX, TensorRT, or OpenVINO. Integrate AI models with embedded firmware and IoT platforms. Work with hardware accelerators such as GPUs, TPUs, and NPUs. Optimize latency, memory usage, and power consumption. Develop edge inference pipelines for real-time applications. Collaborate with AI researchers, embedded engineers, cloud engineers, and product teams. Validate AI model accuracy, robustness, and performance. Maintain technical documentation and deployment pipelines.

Required Skills rtificial Intelligence & Machine Learning Machine Learning Deep Learning Neural Networks Computer Vision Natural Language Processing (NLP) Reinforcement Learning (Preferred) Transfer Learning Model Quantization Model Pruning Knowledge Distillation

Edge AI Frameworks TensorFlow Lite TensorFlow PyTorch ONNX Runtime TensorRT OpenVINO Qualcomm AI Engine SDK NVIDIA JetPack MediaPipe

Programming Languages Python C++ C Java (Preferred) Bash

Embedded Systems Embedded Linux ARM Cortex Raspberry Pi NVIDIA Jetson Google Coral TPU ESP32 STM32 NXP Platforms Qualcomm Snapdragon

Computer Vision OpenCV YOLO SSD Faster R-CNN Image Classification Object Detection Object Tracking Image Segmentation OCR

I Model Optimization Quantization Pruning Mixed Precision Tensor Optimization Edge Inference Hardware Acceleration

IoT & Edge Computing Edge Computing IoT Architecture MQTT OPC UA Edge Gateway Device Management OTA Updates

Cloud Platforms AWS IoT Azure IoT Hub Google Cloud IoT Azure Machine Learning AWS SageMaker Vertex AI

Hardware Accelerators GPU TPU NPU CUDA cuDNN Client Movidius Edge TPU

Version Control & DevOps Git GitHub GitLab Jenkins Docker Kubernetes (Basic) CI/CD

Operating Systems Linux Ubuntu Embedded Linux RTOS (Preferred)

Preferred Qualifications Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Electronics, Embedded Systems, Robotics, or a related field. 3-8+ years of experience in AI/ML and embedded systems. Hands-on experience deploying AI models to edge devices. Strong understanding of computer vision and deep learning.

Preferred Certifications TensorFlow Developer Certificate NVIDIA Deep Learning Institute (DLI) Microsoft Azure AI Engineer Associate (AI-102) Google Professional Machine Learning Engineer AWS Certified Machine Learning - Specialty

Soft Skills Strong analytical and problem-solving skills. Excellent communication and teamwork. Ability to optimize complex AI workloads. Attention to detail. Continuous learning mindset.

Nice to Have Skills Robotics Autonomous Vehicles ROS (Robot Operating System) FPGA Basics CUDA Programming TinyML Federated Learning MLOps AI Security Generative AI at the Edge

Sample Project Responsibilities Deploy YOLO-based object detection on NVIDIA Jetson devices. Optimize TensorFlow models using TensorRT for real-time inference. Develop computer vision applications for smart cameras. Integrate AI with IoT gateways for industrial automation. Build TinyML applications for microcontrollers. Implement OTA model updates for edge devices. Benchmark and optimize inference latency and memory usage. Monitor edge device health and AI performance.

Sample Edge AI Architecture Data Sources Cameras Sensors IoT Devices Industrial Equipment Mobile Devices I Training TensorFlow PyTorch Python GPU Training Model Optimization TensorFlow Lite ONNX TensorRT OpenVINO Edge Deployment NVIDIA Jetson Raspberry Pi Google Coral Qualcomm Edge AI ARM-based Devices Cloud Integration AWS IoT Azure IoT Hub Google Cloud MQTT Broker Monitoring Device Health AI Performance Metrics Logs OTA Updates

Interview Questions I & Machine Learning What is Edge AI, and how does it differ from cloud AI? Explain the difference between machine learning and deep learning. What is model quantization, and why is it important? What is transfer learning?