Company Background

Founded in 2009, the company is a leading cloud software platform designed to enhance the capabilities of commercial construction professionals. Their suite of user-friendly tools aims to optimize workflows, foster collaboration, and provide data-driven insights that facilitate more informed decision-making. By supporting contractors and suppliers through the pre-construction phase, the platform delivers qualified leads, seamless team cooperation, efficient document management, comprehensive bid management solutions, and valuable data insights, all within a fully integrated ecosystem.

Project Description

The client would like to build an ML solution for reading architecture plans and reducing the time necessary to identify and count specific elements of the plan (such as doors, windows, electrical), as well as calculating dimensions and square footage of plan areas. ​The solution will need to provide an API to integrate into the client's application. ​The client's team will own integrating the product with the existing application​. Need it to run on a client's owned infrastructure.

Technologies

• PyTorch
• Computer Vision (OpenCV, Pillow)
• Data Preprocessing, Feature Engineering, Model Evaluation
• Generative AI Models (GANs, VAEs)
• Large Language Models (BERT, RoBERTa, GPT)

What You'll Do

• Design/train deep learning models for object detection and segmentation;
• Collaborate with stakeholders to understand the specific computer vision challenges the project aims to solve;
• Configure AWS services to deploy and manage computer vision models;
• Develop and implement evaluation metrics to assess the performance of object detection and segmentation models;
• Conduct thorough testing to ensure models meet the required standards;
• Oversee the image annotation process, ensuring high quality annotations critical to model training;
• Communicate technical project requirements, progress, and outcomes to non-technical stakeholders, ensuring clear understanding and alignment;
• Participate in technical design sessions to identify/document technical solutions;
• Work with the client to develop solutions based on their specifications;
• Lead the effort for the product;

Job Requirements

• 5+ years' experience in machine learning, computer vision, and software development;
• Proficiency in Deep Learning frameworks such as TensorFlow (including Keras) and/or PyTorch;
• Understanding of computer vision techniques and image processing;
• Experience with Python and relevant libraries (e.g., OpenCV, Pillow);
• Experience with cloud platforms (e.g., AWS);
• Knowledge of data preprocessing, feature engineering, and model evaluation;
• Experience with Generative AI models (e.g., GANs, VAEs) and their applications;
• Familiarity with Large Language Models (LLMs) and their integration with various tasks;
• Possession of an AWS certification will be a plus;
• Level of English - from Upper-Intermediate (spoken/written);

What Do We Offer

The global benefits package includes:

• Technical and non-technical training for professional and personal growth;
• Internal conferences and meetups to learn from industry experts;
• Support and mentorship from an experienced employee to help you professional grow and development;
• Internal startup incubator;
• Health insurance;
• English courses;
• Sports activities to promote a healthy lifestyle;
• Flexible work options, including remote and hybrid opportunities;
• Referral program for bringing in new talent;
• Work anniversary program and additional vacation days.