Data Extraction Engineer (NYC or Remote)

at  Trunk Tools Inc

At Trunk Tools, we are tackling the massive $850B+ construction labor industry. We’re an exceptional team of serial entrepreneurs, brought together by our shared mission: aligning incentives for the deskless workforce. Our founding team (LinkedIn, Uber, SpaceX, YC, Carta, etc.) has successfully built and deployed software in construction for 140k+ users, millions of users beyond the construction space, and worked on +$1 billion of built-environment projects. Within our first year of business, we’ve captured contracts worth $1 million in ARR alongside backing from incredible Seed investors and industry experts. We are extremely excited to be in hyper-growth mode and we hope you join us on our journey to revolutionize the construction industry! We have built a brand new product that requires building, evaluating, and launching innovative solutions leveraging the latest ML/NLP/LLM techniques.

• Develop and Optimize Data Pipelines: Design, construct, install, test, and maintain highly scalable data management systems.
• Expand Parsing Capabilities: Take the initiative to constantly expand the range of file and content types our systems can parse using Vision models, ML, OCR, and more to maximize data capture.
• Leverage LLMs for Data Structuring: Explore and implement the use of Large Language Models (LLMs) to convert unstructured data into structured formats, improving data usability and accessibility.
• Develop Business Logic for Data Routing: Build and optimize business logic for the routing of document and content types to the most effective parsing solutions, including the development of retry logic and error handling procedures to ensure robust data handling.
• Collaborate with Product Teams: Work closely with product teams to experiment with and implement advanced parsing solutions and techniques, ensuring our products meet the high standards our clients expect.