AI-powered invoice reconciliation and procurement automation for construction - ON-1202
Genre de projet: RechercheDiscipline(s) souhaitée(s): Informatique, Sciences mathématiques, Mathématiques, Affaires, Sciences sociales et humaines
Entreprise: Digby Labs
Durée du projet: 4 à 6 mois
Date souhaitée de début: Dès que possible
Langue exigée: Anglais
Emplacement(s): Toronto, ON, Canada
Nombre de postes: 2
Niveau de scolarité désiré: MaîtriseDoctorat
Ouvert aux candidatures de personnes inscrites à un établissement à l’extérieur du Canada: No
Au sujet de l’entreprise:
QuoteToMe is a venture-backed procurement automation platform for construction contractors. The platform digitizes quoting, purchase orders, receiving, and invoice reconciliation for self-performing general contractors and subcontractors across North America. Current integrations include Procore and Viewpoint Vista, serving customers with annual revenue ranging from $15M to $1B+.
Veuillez décrire le projet.:
QuoteToMe is developing an AI-powered procurement intelligence layer spanning three construction lifecycle stages. In pre-construction, the system automates bid leveling and reconciliation by extracting line items from competing bids, normalizing them to a standard scope taxonomy, flagging missing items, and generating comparison matrices. At mid-stage, it handles delivery reconciliation by matching received materials against purchase orders in real time, flagging partial deliveries, substitutions, and over/under-shipments. For invoice and accounts payable, it performs automated three-way matching, discrepancy flagging and redlining, confidence-scored approval recommendations with source document links, and a click-to-pay summary for final sign-off. The intern will work within DigbyLab alongside the QuoteToMe product and data science team, focusing on one of three research areas: (1) an accuracy engine that reads invoices, compares them against POs and deliveries, and produces results with measurable confidence intervals; (2) a cybersecurity framework that keeps procurement data encrypted, auditable, and isolated from training sets; or (3) an integration layer that builds connectors for seamless data flow between QuoteToMe and contractor systems like Procore, Viewpoint, and QuickBooks.
Expertise ou compétences exigées:
Experience with NLP and document AI. Familiarity with LLM application development, API integration, and agentic workflow design. Interest in applied AI for industry (construction tech, fintech, or enterprise SaaS). Strong software engineering fundamentals (Python, cloud infrastructure, CI/CD).
