Machine Learning, Software Engineer (Remote)

About PermitFlow PermitFlow’s mission is to streamline and simplify construction permitting in the $1.6 trillion United States construction market. Our software reduces time to permit, supporting permitting end-to-end including permit research, application preparation, submission, and monitoring. We’ve raised a $31m Series A led by Kleiner Perkins with participation from Initialized Capital, Y Combinator, Felicis Ventures, Altos Ventures, and the founders and executives from Zillow, PlanGrid, Thumbtack, Bluebeam, Uber, Procore, and more. Our team consists of architects, structural engineers, permitting experts, and workflow software specialists, all who have personally experienced the pain of permitting. About the Team We have a lean but mighty engineering team. We’ve done a lot with a little, but there’s much more work to be done to continue our fast-paced growth and we want you to be a part of that growth. You’ll help us get there by owning end-to-end projects, talking with customers, and ultimately supporting the growth of PermitFlow. ✅ What You’ll Do: You'll work alongside the CTO and engineering team to develop the first construction permit application and management platform for builders. Our current team consists of engineers from Uber, bolthires, NerdWallet, OnDeck, Harvard, Stanford, and more. We are background and experience agnostic, and we encourage anyone to apply if they are passionate about joining a small team and working to solve a real-world pain point. We are seeking a Machine Learning Engineer to help build intelligent systems that enhance our permit processing, document understanding, and compliance workflows. You will work on LLM-based models, retrieval-augmented generation (RAG) pipelines, and AI-driven automation, leveraging state-of-the-art techniques to extract, analyze, and structure complex permitting data.

• Design, implement, and optimize LLM-powered models for document processing, data extraction, and permit application workflows.
• Develop and fine-tune retrieval-augmented generation (RAG) pipelines to improve query processing and information retrieval.
• Experiment with pre-trained models and fine-tune them for permit-related NLP tasks, such as document classification and entity recognition.
• Build scalable machine learning infrastructure, integrating with backend systems to support AI-driven workflows.
• Work with large-scale structured and unstructured data to ensure efficient indexing, retrieval, and contextual relevance.
• Monitor and improve the performance and scalability of deployed models.
• Stay updated with the latest research in LLMs, NLP, retrieval systems, and apply best practices to our AI models.
• Collaborate with engineers, product managers, and legal experts to develop AI-native solutions for complex permitting challenges. Qualifications & Fit:
• 3+ years of experience in machine learning engineering, ideally in production environments.
• Strong understanding of LLMs (e.g., OpenAI GPT, Hugging Face models) and their applications.
• Hands-on experience with retrieval systems (e.g., Elasticsearch, FAISS, or vector databases).
• Proficiency in Python and common ML libraries (e.g., TensorFlow, PyTorch, scikit-learn).
• Experience with ML model deployment, monitoring, and scaling in a cloud environment (AWS, GCP, or Azure).
• Strong problem-solving skills and ability to work in a fast-paced, high-ownership environment.

Benefits

• Equity packages
• Competitive Salary
• 100% Paid health, dental & vision coverage
• Home office & equipment stipend
• ️ Lunch & Dinner provided via UberEats w/ a fully stocked kitchen
• Commuter benefits
• Team building events
• Unlimited PTO Apply tot his job

Apply tot his job Apply To this Job