Software Engineer II (Machine Learning Engineer)

Job Description

Overview:

We are looking for a Machine Learning Engineer who will be responsible for improving and maintaining our machine learning models/pipelines, developing scalable ETL pipelines, and optimizing the end-to-end data processing workflow. This role requires strong experience in computer vision, OCR, and deep learning, as well as the ability to deploy models in a production environment.

Responsibilities:

• Design, develop, and maintain data pipelines to manage TIFF images, extracted fields, CSV, PDF, XML, and structured outputs.
• Build and optimize ETL workflows for preprocessing (resizing, rotation, denoising) and ML pipeline integration.
• Develop, train, evaluate, deploy, and monitor deep learning models in a production environment.
• Develop API endpoints and integrate structured data into the existing data keying application.
• Implement logging, monitoring, and error-handling mechanisms for model performance and data consistency.
• Work with Dockerized deployments to streamline ML and data workflows.
• Collaborate with ML engineers, software developers, and quality test engineers to ensure seamless integration

Qualifications:

• 3+ years of experience in data engineering, ML engineering, or a hybrid role.
• Proficiency in Python for data manipulation, API development, and ML integration.
• Ability to write efficient ETL scripts and manage large datasets.
• Strong knowledge of database management (SQL, NoSQL, PostgreSQL, or similar).
• Familiarity with YOLO-based object detection and OCR processing.
• Knowledge of image processing and computer vision tools such as Pillow, OpenCV, pdf2image, etc.
• Experience with training and testing machine learning models using Tensorflow, Pyspark, and Scikit-learn.
• Hands-on experience with Docker, Kubernetes, and containerized ML workflows.
• Experience working with Azure services (Data Factory, Blob Storage, ML Studio, and other compute resources).
• Experience with Flask, FastAPI, or other API frameworks.
• Knowledge of MLOps best practices for deploying and monitoring ML models in production.
• Hands-on experience using Git and Github/Gitlab, and Github Actions.