Ai Ml Engineer

Job Summary:

We are looking for a skilled AI Video Analytics Engineer with hands-on experience in AI-based surveillance, object detection, tracking, and OCR. The ideal candidate will have a strong background in deep learning frameworks (TensorFlow, PyTorch), video processing (GStreamer, FFmpeg), and practical deployment of models using optimization tools like TensorRT. Experience in working with real-time communication protocols and multimedia systems is essential.

Key Responsibilities:

• Design and implement AI solutions for real-time video analytics in surveillance environments.
• Develop and deploy object detection, tracking, and OCR models using YOLO, MobileNetSSD, and other state-of-the-art architectures.
• Optimize models for edge and server deployment using TensorRT and other acceleration frameworks.
• Integrate AI pipelines into video streams using GStreamer and FFmpeg.
• Handle real-time data exchange using protocols like HTTP, MQTT, and TCP/UDP.
• Build and consume RESTful APIs for model inference, alerts, and data flow.
• Collaborate with cross-functional teams to design scalable and efficient systems for POCs and production-grade solutions.
• Work with CCTV/RTSP/ONVIF streams for real-time monitoring and analytics.
• Ensure performance tuning and latency optimization for real-time use cases.

Must-Have:

• Strong experience in Object Detection, Tracking, and OCR using deep learning.
• Proficiency with TensorFlow, PyTorch, and TensorRT. • Hands-on experience with YOLO (v5/v8), MobileNet SSD, or similar architectures.
• Solid knowledge of video streaming frameworks GStreamer, FFmpeg.
• Experience with real-time communication protocols HTTP, MQTT, TCP/UDP.
• Working knowledge of REST API development and consumption.
• Exposure to OpenCV, NumPy, and other computer vision libraries.
• Understanding of AI deployment pipelines for edge and cloud.

Good to Have:

• Experience with ONVIF, RTSP camera integrations.

• Exposure to MLOps tools and practices.

• Familiarity with containerization (Docker) and deployment pipelines (CI/CD).

• Basic knowledge of cloud services (AWS, GCP, Azure).