Computer Vision Engineer

Computer Vision Engineer

About the Company

Our clientis an innovative AI-powered technology company transforming the way contractors estimate and price projects.

Our platform uses artificial intelligence to analyze construction plans, drawings, specifications, and other project documentation to generate accurate, data-driven quotes-helping contractors dramatically reduce the time and effort required to prepare bids.

We work with contractors across multiple trades, including electrical, mechanical, plumbing, and general contracting, and we're building technology that understands complex construction documents in ways that traditional software cannot.

We are looking for a talented Computer Vision Engineer to help us build the AI systems at the core of our platform.

The Opportunity

As a Computer Vision Engineer, you will design, develop, and deploy computer vision and machine learning systems that extract meaningful information from construction drawings and documents.

You'll work on challenging problems such as understanding architectural and engineering drawings, identifying symbols and components, extracting dimensions and quantities, recognizing relationships between objects, and converting unstructured visual information into structured data that can ultimately drive automated estimates and quotes.

This is a highly impactful role for someone who wants to work on real-world computer vision problems with direct commercial impact.

What You'll Do

• Design and develop computer vision and machine learning models for analyzing construction drawings, blueprints, schematics, PDFs, and images.
• Build systems that identify and classify objects, symbols, equipment, components, annotations, dimensions, and other relevant information within construction documents.
• Develop algorithms for object detection, segmentation, OCR, document understanding, and visual classification.
• Extract structured information from electrical and other engineering drawings to support automated quantity takeoffs and estimating.
• Develop techniques for understanding spatial relationships between components and objects within complex drawings.
• Work with multimodal AI/ML approaches combining computer vision, OCR, NLP, and large language models.
• Process and analyze large volumes of construction documents to create training and evaluation datasets.
• Develop data pipelines for image/document preprocessing, annotation, augmentation, training, and evaluation.
• Experiment with state-of-the-art computer vision and multimodal models and determine where they can deliver the greatest business value.
• Improve model accuracy, robustness, inference speed, and scalability in production environments.
• Work closely with software engineers to deploy models into production applications and APIs.
• Collaborate with construction and estimating experts to understand domain-specific challenges and translate them into technical solutions.
• Establish appropriate evaluation metrics and continuously monitor model performance.
• Investigate errors and edge cases and develop strategies to improve model performance.
• Contribute to the architecture and technical direction of the company's AI platform.

Example Problems You'll Solve

You may work on problems such as:

• Automatically identifying electrical symbols on engineering drawings.
• Recognizing panels, transformers, switches, outlets, fixtures, conduits, and other electrical components.
• Determining quantities of components from drawings.
• Understanding floor plans and electrical schematics.
• Extracting measurements and dimensions from plans.
• Linking symbols and components to their corresponding schedules or specifications.
• Understanding relationships between electrical components and circuits.
• Distinguishing between similar symbols used across different drawing standards.
• Converting a collection of drawings into structured project data that can be used to generate an estimate.
• Combining visual information from drawings with text from specifications and project documents.
• Detecting and handling revisions between different versions of construction plans.

Required Qualifications

• Bachelor's or Master's degree in Computer Science, Computer Engineering, Electrical Engineering, Mathematics, or a related technical field.
• 3+ years of professional experience in computer vision, machine learning, or applied AI.
• Strong understanding of computer vision fundamentals and deep learning.
• Hands-on experience with frameworks such as PyTorch, TensorFlow, or similar.
• Strong Python programming skills.
• Experience with modern computer vision techniques, including object detection, image classification, segmentation, and/or OCR.
• Experience training, evaluating, and deploying machine learning models.
• Strong understanding of model evaluation, data quality, and experimentation.
• Experience working with large and/or complex image or document datasets.
• Ability to take ML models from research/prototype through production.
• Strong problem-solving and analytical skills.

Preferred Qualifications

• Experience with construction technology, AEC, engineering, CAD, BIM, or estimating software.
• Experience working with architectural, mechanical, electrical, or engineering drawings.
• Knowledge of electrical plans, schematics, or construction documentation.
• Experience with document AI, intelligent document processing, or multimodal AI.
• Experience with OCR technologies such as Tesseract, PaddleOCR, Google Document AI, AWS Textract, or similar.
• Experience with object detection frameworks such as YOLO, Detectron2, MMDetection, or similar.
• Experience with vision-language models or multimodal LLMs.
• Experience with vector databases, embeddings, RAG, or LLM-based document understanding.
• Experience processing PDFs and high-resolution technical drawings.
• Familiarity with CAD formats, computer-aided design, or BIM data.
• Experience deploying ML models using cloud platforms such as AWS, Azure, or GCP.
• Experience with Docker, Kubernetes, and modern ML deployment infrastructure.

Technology Environment

Depending on your experience, you may work with technologies including:

Languages: Python, SQL, C++

ML/AI: PyTorch, TensorFlow, Hugging Face, OpenCV

Computer Vision: YOLO, Detectron2, segmentation models, OCR, image processing

AI: Vision-Language Models, LLMs, multimodal models, embeddings

Cloud: AWS / Azure / GCP

Infrastructure: Docker, Kubernetes, REST APIs, GPU infrastructure

Data: PostgreSQL, vector databases, data pipelines, cloud storage

We're less concerned about whether you've used every technology listed above and more interested in your ability to learn quickly, solve difficult problems, and build production-quality AI systems.