Edge AI Engineer - Job DescriptionJob Title Edge AI Engineer
Location [City/Remote/Hybrid]
Employment Type Full-time / Contract
Job Summary We are seeking an Edge AI Engineer to design, develop, optimize, and deploy artificial intelligence and machine learning models on edge devices. The ideal candidate will have expertise in embedded systems, computer vision, deep learning, model optimization, and edge computing technologies. This role focuses on building low-latency, power-efficient AI applications for IoT devices, industrial automation, robotics, healthcare, automotive, and smart infrastructure.
Key Responsibilities - Design, develop, and deploy AI/ML models for edge devices and embedded systems.
- Optimize deep learning models for low-latency, memory-efficient, and power-efficient inference.
- Convert and deploy models using frameworks such as TensorFlow Lite, ONNX Runtime, TensorRT, and OpenVINO.
- Develop AI applications for computer vision, speech processing, sensor analytics, and real-time decision-making.
- Integrate AI models with embedded hardware, IoT devices, and edge computing platforms.
- Collaborate with hardware engineers, firmware developers, software engineers, and data scientists to deliver end-to-end edge AI solutions.
- Develop and optimize inference pipelines for GPUs, NPUs, TPUs, DSPs, and microcontrollers.
- Perform model benchmarking, profiling, quantization, pruning, and performance tuning.
- Implement secure model deployment, over-the-air (OTA) updates, and device lifecycle management.
- Build APIs and edge services for AI-enabled applications.
- Monitor deployed edge AI systems and continuously improve performance, reliability, and resource utilization.
- Stay current with advancements in edge computing, embedded AI, AI accelerators, and TinyML technologies.
Required Qualifications - Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Electronics, Embedded Systems, Electrical Engineering, Robotics, or a related field.
- 3-8+ years of experience in AI/ML, embedded systems, edge computing, or software engineering.
- Strong proficiency in Python and C/C++.
- Experience developing and deploying machine learning and deep learning models.
- Knowledge of embedded Linux, real-time operating systems (RTOS), and IoT architectures.
- Experience with model optimization and deployment frameworks.
- Familiarity with computer vision, signal processing, or sensor fusion applications.
- Strong understanding of software engineering principles, debugging, and performance optimization.
Preferred Qualifications - Experience with NVIDIA Jetson, Raspberry Pi, Qualcomm AI platforms, Client Movidius, Google Coral, or similar edge hardware.
- Knowledge of TinyML and microcontroller-based AI deployments.
- Experience with robotics, autonomous systems, or industrial automation.
- Familiarity with MLOps for edge deployments and fleet management.
- Experience with cloud-edge integration and edge orchestration platforms.
- Relevant AI, embedded systems, or cloud certifications.
Technical Skills - Python
- C/C++
- Embedded Linux
- RTOS
- TensorFlow Lite
- TensorFlow
- PyTorch
- ONNX Runtime
- TensorRT
- OpenVINO
- OpenCV
- CUDA
- NVIDIA Jetson
- Raspberry Pi
- Google Coral
- Client Movidius
- Qualcomm AI SDK
- TinyML
- Edge Impulse
- MQTT
- Docker
- Kubernetes
- REST APIs
- Git
- CI/CD
- Computer Vision
- Deep Learning
- Model Quantization
- Model Pruning
- Edge Computing
- IoT
Soft Skills - Analytical thinking
- Problem-solving
- Cross-functional collaboration
- Communication
- Innovation
- Adaptability
- Time management
- Attention to detail
- Continuous learning
Key Deliverables - Production-ready edge AI applications
- Optimized AI models for embedded deployment
- Real-time inference pipelines
- Device integration and deployment solutions
- Performance benchmarking reports
- Technical documentation
- Secure deployment and update mechanisms
- Monitoring and maintenance plans
Success Metrics - AI inference latency and throughput
- Model accuracy after optimization
- Memory and power efficiency
- Successful deployment across target edge devices
- Device reliability and uptime
- Reduction in deployment and maintenance effort
- Compliance with security and quality standards
- Timely delivery of edge AI features and enhancements
