Machine Learning Engineer

Job Summary:We are looking for an Machine Learning Engineer with 1–2 years of experience building production machine learning systems, with a strong computer vision focus, to join our AI/ML team.You will work on building a computer vision pipeline that automatically extracts structured digital data from scanned images. The work spans image preprocessing, layout and text detection, segmentation, algorithmic post-processing and data export, and requires accurate, reliable results on real-world, imperfect inputs.The ideal candidate has a strong foundation in Python and deep learning for computer vision, enjoys solving open-ended problems, and can turn machine learning ideas into reliable, modular and scalable software.Job ResponsibilitiesDesign, build and deploy an end-to-end computer vision pipeline that extracts structured data from scanned images: preprocessing, layout detection, text and scale reading (OCR), segmentation, post-processing and data export.Train and fine-tune deep learning models for image segmentation, detection and classification (e.g., U-Net, SAM-based or instance segmentation models).Prepare, annotate, augment and generate image datasets, including synthetic data, for model training and evaluation.Develop image processing and algorithmic post-processing methods (e.g., dynamic programming, tracking, graph-based methods) that turn model outputs into accurate structured results.Apply supervised, unsupervised and self-supervised learning techniques for feature extraction, quality estimation and continuous model improvement.Evaluate on real, hand-verified samples using task-specific accuracy metrics in addition to IoU and Dice, and optimize for accuracy, performance and latency.Write clean, modular, tested code and contribute to deployment, monitoring and model versioning.Collaborate with engineers and domain experts to define requirements, edge cases and quality checks.Required SkillsStrong Python programming and software development principles (OOP, testing, Git).Hands-on experience training deep learning models for computer vision in PyTorch and/or TensorFlow, including segmentation or detection models.Solid image processing fundamentals (OpenCV, scikit-image): deskewing, thresholding, morphology and geometric transforms.Experience with data preparation, augmentation and evaluation for computer vision models.Ability to combine learned models with algorithmic post-processing in a multi-stage pipeline.Experience developing and deploying production-level machine learning systems, with basic MLOps practices.Strong analytical, problem-solving and learning skills.Preferred SkillsExperience with OCR (PaddleOCR, Tesseract, TrOCR) or vision-language models.Experience with instance segmentation or thin-structure segmentation.Experience with synthetic data generation or generative models (GANs, diffusion).Experience with active learning, uncertainty estimation or tracking algorithms.Experience handling large images (tiling) and optimizing GPU training.ExperienceMinimum: 1-2 years developing and deploying production-level machine learning algorithmsPreferred: Experience with deep learning based image segmentation (U-Net) and computer vision pipelinesEducation/QualificationMinimum: Bsc Computer SciencePreferred: Master's degree in AI/ML, Computer Science, Data Science, or a related field.LocationIslamabad (On-site)