About the position
We are seeking a Machine Learning Vision Engineer to design and implement advanced OCR and computer vision solutions that power large-scale, real-time image-based transaction processing. This role blends software engineering best practices with applied ML to deliver scalable, production-ready systems that integrate seamlessly into distributed architectures.
Responsibilities
• Design, implement, and optimize ML-based computer vision components, including object detection, image classification, OCR pipelines, and image quality assessment classifiers.
• Develop robust, production-ready Python code leveraging Object Oriented Design (OOD) principles.
• Collaborate with system architects to integrate ML components into distributed, message-driven architectures.
• Implement training, evaluation, and feedback loops for OCR and image classifiers.
• Optimize models for performance in near real-time transaction workflows with low latency and high throughput.
• Participate in system-level design discussions to ensure scalability, maintainability, and adaptability.
• Work closely with database, API, and DevOps teams for smooth deployment and testing.
• Build frameworks and systems suitable for production, beyond proof-of-concept work.
• Fully document technical and functional designs, test plans, impact analysis, lessons learned, and best practices.
• Develop and maintain productive relationships with technical teams, business stakeholders, vendors, and clients.
• Lead and participate in project team activities related to enterprise system enhancements.
• Work independently to complete assigned tasks and responsibilities.
• Adhere to organizational standards, policies, and procedures.
• Utilize various software and technology tools as needed for job duties.
• Perform other related duties as assigned.
Requirements
• Strong professional experience with Python (must be clearly demonstrated in resume).
• Solid background in software engineering: Object Oriented Programming (OOP), design patterns, clean code, and testable architectures.
• Experience with image processing and computer vision frameworks (e.g., OpenCV, Pillow).
• Hands-on experience with machine learning frameworks (e.g., PyTorch, TensorFlow).
• OCR-related experience (such as Tesseract, PaddleOCR, EasyOCR, or custom models).
• Familiarity with object detection frameworks (e.g., YOLO, Faster R-CNN, SSD).
• Knowledge of classification, feature extraction, and evaluation metrics for vision tasks.
• Proficient with Microsoft Office 365 suite (Teams, Word, Excel, PowerPoint) and Microsoft ADO Testing Module.
• Bachelor’s degree in business management or information systems, or an equivalent combination of education and experience.