Computer Vision Engineer

OON Systems LLC; New York (NY); Hybrid; USD 120,000 - 160,000; Full time

Job summary

OON Systems LLC in New York, NY is seeking a Computer Vision Engineer to design and deploy document understanding, OCR, and data extraction systems for healthcare data.

You will work end-to-end from preprocessing and model training to production deployment, collaborating with ML and software teams to integrate vision pipelines into platform workflows.

Qualifications

• Strong Python skills and experience with OpenCV, PyTorch, or TensorFlow.
• Experience with CNNs, object detection, segmentation, or OCR systems.
• Experience deploying models in production environments.

Responsibilities

• Design and build computer vision pipelines for document parsing, OCR, and classification.
• Train and optimize models for healthcare document understanding and data extraction.
• Develop preprocessing, augmentation, and evaluation strategies for real-world image and document data.
• Deploy vision models into production with monitoring, versioning, and reliability engineering.
• Collaborate with ML and software engineering teams to integrate vision systems into platform workflows.

Skills

Python

OpenCV

PyTorch

TensorFlow

CNNs/Segmentation

OCR Systems

Cloud deployment

Tools

AWS

GCP

Docker

Job description

OON Systems processes large volumes of complex healthcare documents and data. As a Computer Vision Engineer, you will design and deploy systems for document understanding, optical character recognition, image classification, and structured data extraction from unstructured sources.

You will work across the full pipeline — from image preprocessing and model training to deployment and monitoring in production.

Responsibilities

• Design and build computer vision pipelines for document parsing, OCR, and classification
• Train and optimize models for healthcare document understanding and data extraction
• Develop preprocessing, augmentation, and evaluation strategies for real-world image and document data
• Deploy vision models into production with monitoring, versioning, and reliability engineering
• Collaborate with ML and software engineering teams to integrate vision systems into platform workflows

Qualifications

• Strong Python skills and experience with computer vision frameworks (OpenCV, PyTorch, TensorFlow)
• Experience with CNNs, object detection, segmentation, or OCR systems
• Understanding of image preprocessing, data augmentation, and model evaluation
• Experience deploying models in production environments
• Strong problem-solving skills and attention to detail

Preferred Qualifications

• Experience with document AI, layout parsing, or medical image analysis
• Experience with transformer-based vision models (ViT, DETR, LayoutLM)
• Familiarity with cloud-based ML deployment (AWS, GCP)

About You

• Detail-oriented
• Comfortable with messy real-world data
• Able to iterate quickly from prototype to production