Machine Learning Engineer – Data Extraction (NYC or Remote US) at Trunk Tools #vacancy #remote

At Trunk Tools, we are tackling the massive $13 trillion+ construction industry. We’re an exceptional team of serial entrepreneurs, brought together by our shared mission: automating construction. Our founding team (SpaceX, Stanford, MIT, Carta, etc.) has successfully built and deployed software in construction for 140k+ users, millions of users beyond the construction space, and worked on +$2 billion of built-environment projects. We aren’t another out-of-touch tech startup, most of our team comes from construction. We spent the last few years building the brain behind construction. Now we are deploying workflows/ agents, starting with Q&A document chatbot, to be ingrained in construction teams’ workflows, ultimately to automate construction. Given our immense traction with several Fortune 500 construction companies, we are doubling our team in order to deploy several more agents this year. You will have an opportunity to drive the transformation of a multi-trillion-dollar industry full of waste, risks and inefficiencies. What you will do and achieve: 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. Who you are: BA/BS in computer science or related degree. Bonus points for a graduate degree. 5+ years of experience Possess extensive experience in data parsing, including working with various file types and formats, and have a deep understanding of the technical challenges involved. Have hands-on experience with Large Language Models and understand how to leverage them for improving data extraction and structuring processes. Have experience with Retrieval-Augmented Generation systems and understand how they can be applied to enhance data extraction and processing workflows. Adept at developing sophisticated business logic for data routing and have experience implementing robust retry logic and error-handling mechanisms. What we offer A close-knit and collaborative early-stage startup environment where every voice is heard and every opinion matters; currently we’re 17 team members Competitive salary and stock option equity packages 3 Medical Plans to choose from including 100% covered option. Plus Dental and Vision Insurance! Learning & Growth stipend Flexible long-term work options (remote and hybrid) 401K Free lunch provided in the office in NYC – you’ll never go hungry with us! Unlimited PTO; We truly believe in work-life balance and that hard work should be balanced with time for rest and rejuvenation IRL / In-Person retreats throughout the year Salary range: $170,000 – $240,000 / year + equity We realize applying for jobs can feel daunting at times. We don’t expect you to check all the qualification boxes and encourage you to apply if you have experience in some of the areas. At Trunk Tools, we’re working hard to build a more productive and safer environment within the construction industry, and we strive to live by these same values here at Trunk Tools HQ. As an equal-opportunity employer, we are committed to building an inclusive environment where you can be you. We work hard to evaluate all employees and job applicants consistently, without regard to race, color, religion, gender, national origin, age, disability, pregnancy, gender expression or identity, sexual orientation, or any other legally protected class.

Machine Learning ocr LLM

Leave a Reply