Lucent Innovation - Computer Vision Engineer - Deep Learning/Machine Learning

Job Description

Description Job Title : Computer Vision Engineer Experience : 23 Years About The Role We are seeking a talented Computer Vision Engineer with 23 years of hands-on experience in developing, implementing, and optimizing computer vision and deep learning models. You will work on cutting-edge image and video analytics projects, develop real-time algorithms, and collaborate with cross-functional teams to ship production-ready solutions. This role offers an exciting opportunity to work on innovative applications across AI-driven automation, object detection, image classification, OCR, and more. Key Responsibilities : Vision & Deep Learning Development : Develop and implement computer vision algorithms for image classification, object detection, segmentation, tracking, and related tasks. Build, train, and optimize deep learning models using frameworks such as TensorFlow, Keras, PyTorch, OpenCV. Implement real-time inference pipelines for edge devices, desktop, or cloud environments. Data Pipeline & Preprocessing Collect, preprocess, and annotate large image/video datasets. Perform data augmentation, normalization, and dataset balancing. Work with tools like LabelImg, COCO format, Roboflow, etc. Model Optimization & Deployment Optimize models for performance, speed, and accuracy (quantization, pruning, ONNX conversion). Deploy models on production environments such as NVIDIA GPUs, TensorRT, ONNX Runtime, Docker, AWS/GCP/Azure. Develop scalable APIs or microservices to serve CV models. Research & Innovation - Experience deploying CV models with REST APIs (Flask/FastAPI). Stay updated with recent advancements in CV architectures (YOLO, DETR, Mask R-CNN, Vision Transformers, etc. Experiment with state-of-the-art techniques and propose improvements for model performance. Contribute to building reusable modules, libraries, and internal CV & Documentation : Work closely with product, engineering, and QA teams to understand project goals and define scalable solutions. Document algorithms, model performance metrics, and deployment procedures. Participate in code reviews and contribute to team knowledge Skills & Experience Skills : 2 - 3 years of experience in Computer Vision, Deep Learning, or ML engineering. Strong proficiency in Python and libraries such as NumPy, OpenCV, Pillow. Hands-on experience with PyTorch and/or TensorFlow/Keras. Experience with CV tasks such as : Object detection (YOLO, SSD, Faster R-CNN) Segmentation (UNet, Mask R-CNN) OCR (Tesseract, EasyOCR, CRNN-based models) Feature extraction & image enhancement Familiarity with Git, cloud platforms (AWS/GCP), and Linux environments. Soft Skills Strong problem-solving and analytical skills. Ability to translate business needs into technical solutions. Excellent communication and teamwork. A continuous learning mindset with passion for AI/ML / Bonus Skills : Knowledge of Edge AI : Jetson Nano/Xavier, Coral TPU, Raspberry Pi. Experience with MLOps, Docker, CI/CD pipelines. Understanding of 3D vision (structure from motion, depth estimation). Experience working with time-series video analytics (ref:hirist.tech)