ML Engineer — Computer Vision

OvrScope, Inc.; Denver (CO); Hybrid; USD 120.000 - 160.000; Vollzeit

Zusammenfassung

OvrScope, Inc. seeks a seasoned Computer Vision / Document Understanding engineer to own the data collection, model architecture, evaluation, and production inference under real latency and cost constraints. You will drive data labeling strategies, OCR integration, and layout-aware models from development to deployment.

The role emphasizes building in production, handling unlabeled data, and delivering end-to-end solutions for roofing imagery and estimate PDFs with scalable, efficient inference.

Qualifikationen

• 4+ years building computer vision or document-understanding systems in production.
• Strong Python and PyTorch, plus practical experience with OCR and layout-aware models.
• Have owned a model in production, including non-ideal parts.
• Comfort working without a labeled dataset handed to you.

Aufgaben

• Train and evaluate detection and document-understanding models on roofing imagery and estimate PDFs.
• Design labeling strategy and quality controls for a specialized domain with few public datasets.
• Build evaluation harnesses that reflect claim outcomes, not just benchmark scores.
• Deploy models behind FastAPI services with monitoring, versioning, and rollback.
• Optimize inference cost and latency for documents that can run hundreds of pages.
• Close the loop from production errors back into training data.

Kenntnisse

Python

PyTorch

OCR

Layout-aware models

Production deployment

Tools

FastAPI

Jobbeschreibung

Our vision stack turns photographs and scanned estimates into structured data. It reads scope documents, spots damage that adjusters missed, and links what it finds to specific line items.

You will own that stack end to end: data collection and labeling strategy, model architecture, evaluation, and production inference under real latency and cost constraints.

Modeling

• Train and evaluate detection and document-understanding models on roofing imagery and estimate PDFs.
• Design labeling strategy and quality controls for a specialized domain with few public datasets.
• Build evaluation harnesses that reflect claim outcomes, not just benchmark scores.

Production

• Deploy models behind our FastAPI services with monitoring, versioning, and rollback.
• Optimize inference cost and latency for documents that can run hundreds of pages.
• Close the loop from production errors back into training data.

Requirements

• 4+ years building computer vision or document-understanding systems in production.
• Strong Python and PyTorch, plus practical experience with OCR and layout-aware models.
• You have owned a model in production, including the parts that were not fun.
• Comfort working without a labeled dataset handed to you.