5+ years of machine learning engineering experience with production skills
Deep expertise in NLP and LLMs (e.g., OpenAI GPT, Claude)
Background in building retrieval and vector search systems like FAISS or Elasticsearch
Proficient in Python and ML frameworks such as PyTorch or TensorFlow
Proven track record of deploying scalable ML systems for business outcomes
Experience with cloud ML infrastructure (AWS, GCP, or Azure)
Strong systems design with a focus on quick iteration and deployment
Comfortable in a fast-paced startup environment with high autonomy
Responsibilities
Design and optimize LLM-powered models for document processing
Develop RAG pipelines for jurisdictional and regulatory data
Prototype and fine-tune models for NLP tasks like classification
Build and integrate scalable ML infrastructure into production systems
Work with large datasets to enhance indexing and retrieval accuracy
Own the full ML lifecycle from deployment to evaluation
Collaborate with cross-functional teams to create ML solutions for construction challenges
Benefits
Comprehensive medical, dental, and vision coverage
Flexible PTO and paid family leave
Home office & equipment stipend
Hybrid work model with 3 days in-office per week
In-office lunches and dinners provided
Full Job Description
Our HQ is in New York City with a hybrid schedule (3 in-office days per week). Preference for NYC-based candidates or those open to relocation.
Role Overview
As an Applied Machine Learning Engineer, you will develop the ML foundation for PermitFlow's AI agents. You'll design, prototype, and deploy intelligent systems that process documents, extract insights, and power autonomous permitting workflows. You will own the end-to-end ML lifecycle, from model research and data engineering to production deployment and continuous evaluation.
What You'll Do
Design, implement, and optimize LLM-powered models for document processing, data extraction, and permit workflow automation
Develop retrieval-augmented generation (RAG) pipelines and search/retrieval systems for jurisdictional and regulatory data
Rapidly prototype, fine-tune, and evaluate pre-trained models for real-world NLP tasks like classification, entity recognition, and summarization
Build scalable ML infrastructure and backend services, integrating models into production systems that power AI agents
Work with large structured and unstructured datasets to improve indexing, retrieval, and contextual accuracy
Own the full ML lifecycle: experimentation, deployment, monitoring, evaluation, and iteration
Balance ML, retrieval, and rule-based approaches to ship reliable, maintainable, and high-impact AI features
Collaborate with engineering, product, and domain experts to shape ML-powered solutions for complex pre-construction challenges
What We're Looking For
5+ years of experience in machine learning engineering, with production ML experience
Deep expertise in NLP and LLMs (OpenAI GPT, Claude, Hugging Face models)
Experience building retrieval and vector search systems (e.g., FAISS, Elasticsearch, Pinecone, Weaviate)
Proficiency in Python and ML frameworks like PyTorch or TensorFlow
Strong track record of deploying and scaling ML systems with measurable business impact
Experience with cloud ML infrastructure (AWS, GCP, or Azure)
Strong system design and architectural thinking, with a bias toward shipping and iterating quickly
Comfort operating in fast-moving startup environments with high ownership and autonomy
What We Offer
Competitive salary and meaningful equity in a high-growth company
100% company-paid base medical, dental, and vision coverage for employees + healthcare FSA
