- •
Design, develop, and maintain production-grade AI-powered video analytics applications for real-time video processing.
- •
Architect and build scalable end-to-end video analytics pipelines using GStreamer, DeepStream, OpenCV, FFmpeg, and RTSP/HTTP streaming protocols.
- •
Develop and optimize computer vision solutions for object detection, multi-object tracking, image classification, semantic/instance segmentation, face analytics, license plate recognition, and activity recognition.
- •
Optimize AI inference performance using NVIDIA TensorRT, CUDA, ONNX Runtime, DeepStream SDK, and GPU acceleration techniques to maximize throughput and minimize latency.
- •
Deploy, configure, and maintain video analytics applications on NVIDIA Jetson platforms, edge AI devices, and GPU-based Linux servers.
- •
Design and deploy large-scale video analytics solutions supporting hundreds to thousands of IP cameras in production environments with high availability and fault tolerance.
- •
Integrate AI applications with IP cameras, CCTV systems, VMS platforms, cloud services, databases, message brokers, REST APIs, and backend microservices.
- •
Develop robust streaming pipelines capable of handling multiple concurrent video streams with efficient resource utilization, batching, and hardware acceleration.
- •
Profile and optimize CPU, GPU, memory, and network performance to improve system scalability, reliability, and real-time processing capabilities.
- •
Troubleshoot complex production issues related to video streaming, DeepStream pipelines, GStreamer plugins, AI inference, hardware acceleration, and distributed deployments.
- •
Collaborate closely with AI/ML Engineers, Backend Developers, Embedded Engineers, DevOps, and QA teams throughout the product lifecycle.
- •
Mentor junior engineers through technical guidance, architecture reviews, code reviews, debugging support, and engineering best practices.
- •
Contribute to software architecture decisions, technical documentation, coding standards, CI/CD practices, and system design improvements.
- •
Evaluate and adopt emerging technologies in Computer Vision, Edge AI, GPU computing, and Video Analytics to continuously improve the product.
- •
Ensure production readiness by implementing monitoring, logging, automated recovery mechanisms, health checks, and performance benchmarking.