Computer Vision Engineer

We are looking for a Computer Vision Engineer with 3 to 4 years of experience who can design, train, optimize, and deploy computer vision models into production.

The role focuses on image and video understanding, deep learning, and real-time inference systems. You will work end to end, from dataset preparation and model training to deployment and monitoring.

• Build and train models for:
• Image classification
• Object detection
• Segmentation
• Object tracking
• OCR / visual understanding
• Fine-tune pre-trained vision models
• Perform error analysis and improve models based on data

• Prepare and preprocess image and video datasets
• Work with annotations, augmentations, class imbalance, and label quality
• Design proper train/validation/test splits
• Track experiments and model versions

• Deploy models as APIs, batch jobs, or real-time video pipelines
• Optimize inference for:
• Latency
• Throughput
• GPU usage
• Cost
• Work with tools such as ONNX, TensorRT, or TorchScript
• Monitor deployed models and retrain when needed

• 3 to 4 years of experience in computer vision / deep learning
• Strong proficiency in Python
• Strong experience with:
• PyTorch and/or TensorFlow
• OpenCV
• torchvision or similar CV libraries
• Good understanding of:
• CNNs and Vision Transformers
• Object detection and segmentation
• Transfer learning
• Model evaluation metrics such as Precision, Recall, IoU, and mAP
• Experience deploying models into production
• Familiarity with:
• Docker
• Linux
• GPU inference
• ONNX / TensorRT
• Ability to write maintainable production code, not just notebooks

• Experience with real-time video analytics
• Experience with RTSP / CCTV camera streams
• Experience with tracking algorithms such as ByteTrack or DeepSORT
• Experience with NVIDIA GPUs or Jetson devices
• Familiarity with MLOps tools such as MLflow, Weights & Biases, or DVC