Computer Vision Engineer

About Role

We are looking for a skilled Computer Vision Engineer to design and implement cutting-edge CV algorithms and models for real-world applications such as object detection, image classification, video analytics, OCR, and more. You will work on projects involving YOLO, OpenCV, deep learning, and real-time image/video processing. Be able to apply GenAI models as part of the solution. Could also include but not limited to deep learning, neural networks, chatbots, image processing.

Experience:

Job Location:

Office Hours:

Roles and Responsibilities

·       4+ years of experience applying AI to practical uses

·       Develop and train computer vision models for tasks like:

·       Object detection and tracking (YOLO, Faster R-CNN, etc.)

·       Image classification, segmentation, OCR (e.g., PaddleOCR, Tesseract)

·       Face recognition/blurring, anomaly detection, etc.

·       Optimize models for performance on edge devices (e.g., NVIDIA Jetson, OpenVINO, TensorRT).

·       Process and annotate image/video datasets; apply data augmentation techniques.

·       Proficiency in Large Language Models.

·       Strong understanding of statistical analysis and machine learning algorithms.

·       Hands-on implementing various machine learning algorithms such as linear regression, logistic regression, decision trees, and clustering algorithms.

·       Understanding of image processing concepts (thresholding, contour detection, transformations, etc.)

·       Experience in model optimization, quantization, or deploying to edge (Jetson Nano/Xavier, Coral, etc.)

·       Strong programming skills in Python (or C++), with expertise in:

·       Implement and optimize machine learning pipelines and workflows for seamless integration into production systems.

·       Hands-on experience with at least one real-time CV application (e.g., surveillance, retail analytics, industrial inspection, AR/VR).

·       OpenCV, NumPy, PyTorch/TensorFlow

·       Computer vision models like YOLOv5/v8, Mask R-CNN, DeepSORT

·       Engage with multiple teams and contribute on key decisions.

·       Expected to provide solutions to problems that apply across multiple teams.

·       Lead the implementation of large language models in AI applications.

·       Research and apply cutting-edge AI techniques to enhance system performance.

·       Contribute to the development and deployment of AI solutions across various domains

Education/Qualification (if any Certification):

Bachelor’s degree in Computer Science, Information Technology, or a related field.

Requirements:

·       Design, develop, and deploy ML models for:

·       OCR-based text extraction from scanned documents (PDFs, images)

·       Table and line-item detection in invoices, receipts, and forms

·       Named entity recognition (NER) and information classification

·       Evaluate and integrate third-party OCR tools (e.g., Tesseract, Google Vision API, AWS Textract, Azure OCR,PaddleOCR, EasyOCR)

·       Develop pre-processing and post-processing pipelines for noisy image/text data

·       Familiarity with video analytics platforms (e.g., DeepStream, Streamlit-based dashboards).

·       Experience with MLOps tools (MLflow, ONNX, Triton Inference Server).

·       Background in academic CV research or published papers.

·       Knowledge of GPU acceleration, CUDA, or hardware integration (cameras, sensors).