Senior ML Engineer (Document and Image Processing)

Senior Machine Learning Engineer (Document and Image Processing)
Location: Remote
Employment Type: W2 / C2C
Experience Level: 10+ years (Requires at least 2 years of stay in the U.S.A)


VA Tech Solutions is seeking a Senior Machine Learning Engineer with deep expertise in document and image processing. This role will drive the development of end-to-end machine learning pipelines for scanned documents and unstructured image data, while applying strong ML fundamentals such as feature engineering, model selection, hyperparameter tuning, and evaluation metrics.

• Key Responsibilities

  • Develop machine learning pipelines for document classification, OCR, layout detection, and key-value extraction using computer vision and NLP techniques

  • Perform data preprocessing, feature extraction, and augmentation tailored to document and image formats

  • Train and optimize models using AWS SageMaker, managing full ML lifecycle from experimentation to deployment

  • Implement and maintain CI/CD pipelines using GitLab for model retraining and integration with production services

  • Build and manage cloud infrastructure using Terraform and Ansible to support scalable document processing workflows

  • Apply model evaluation techniques such as cross-validation, precision/recall, F1-score, and confusion matrices to ensure robust performance

  • Incorporate techniques for model interpretability, drift detection, and continuous improvement

  • Collaborate in Agile teams with data scientists and engineers to ensure ML models are deployed, monitored, and improved over time

  ---

  Required Qualifications

  • 10+ years of professional experience in machine learning or data science, with a focus on document/image understanding

  • Good to have MicroSoft DiT and OCR (Document Image Transformers)

  • Strong proficiency in Python, along with libraries such as NumPy, Pandas, Scikit-learn, OpenCV, and TensorFlow or PyTorch

  • Solid understanding of supervised and unsupervised learning, model tuning, feature importance, and bias/variance trade-offs

  • Hands-on experience with AWS ML tools including SageMaker, Lambda, S3, Step Functions, and CloudWatch

  • Familiarity with containerization (Docker) and orchestration tools (Kubernetes on AWS EKS)

  • Experience implementing monitoring and logging for deployed ML models

  • Comfort with code quality tools and DevOps practices for ML pipelines (Terraform, Ansible, GitLab CI/CD)