Key Responsibilities

• Design and implement real-time video analytics pipelines for production systems
• Develop and optimize computer vision and deep learning models to achieve low latency and high performance
• Lead feature development from research and prototype stages through deployment and monitoring
• Conduct model profiling, benchmarking, and performance optimization in production environments
• Contribute to system architecture, technical design, and code quality reviews
• Support and guide junior engineers while promoting strong software engineering practices
• Work closely with product, infrastructure, and deployment teams to deliver solutions

Required Qualifications

• Bachelor’s degree in Computer Science, Data Science, Engineering, or a related field
• Minimum 3 years of experience building Vision AI or computer vision applications
• At least 3 years working with machine learning or deep neural networks using frameworks such as TensorRT, TensorFlow, Keras, or PyTorch
• Minimum 2 years of professional experience with C++

Technical Skills

• Programming: C++, Python
• Computer Vision: OpenCV
• Deep Learning Frameworks: PyTorch, TensorFlow, Keras
• GPU Acceleration & Optimization: CUDA, cuDNN, TensorRT
• Model Deployment & Optimization: ONNX, quantization, pruning, FP16/INT8 inference
• Vision AI Techniques: object detection, classification, segmentation, multi-object tracking

Personal Attributes

• Strong problem-solving mindset and ability to learn quickly
• Comfortable working in a small, collaborative engineering team
• Detail-oriented with a strong interest in emerging AI technologies
• Able to take ownership of features and technical challenges end-to-end