Applied ML Engineer: AI for Permitting Workflows

PermitFlow; New York (NY); Hybrid; USD 180,000 - 250,000; Full time

Benefits offered by this job

Competitive salary + equity

Excellent medical coverage

401(k)

Unlimited PTO

Home office stipend

Daily in-office meals

Commuter benefits

Job summary

PermitFlow, an applied AI company redefining permitting processes, seeks an Applied Machine Learning Engineer in NYC. You will design, prototype, and deploy ML systems powering autonomous permitting workflows, handling documents, insights, and end-to-end ML lifecycle.

You will work on retrieval-augmented pipelines, regression and classification tasks, and scalable backend ML infrastructure, collaborating across teams in a fast-paced startup environment.

Qualifications

• 5+ years of ML engineering with production deployment experience.
• Deep NLP/LLM expertise and familiarity with OpenAI GPT, Claude, or Hugging Face.
• Experience building retrieval and vector search systems.

Responsibilities

• Design, implement, and optimize LLM-powered document processing models.
• Build RAG pipelines and search systems for regulatory data.
• Prototype and tune models for NLP tasks like classification and summarization.
• Develop scalable ML infra and production services for AI agents.
• Work with structured/unstructured data to improve indexing and retrieval.
• Own the end-to-end ML lifecycle: experiments, deployment, monitoring.
• Balance ML, retrieval, and rule-based approaches for reliable features.
• Collaborate with engineering, product, and domain experts on pre-construction ML solutions.

Skills

NLP/LLMs expertise

Production ML

Python

Cloud ML infra

System design

Tools

FAISS

Elasticsearch

Pinecone

Weaviate

PyTorch

TensorFlow

Job description

PermitFlow, an applied AI company redefining permitting processes, seeks an Applied Machine Learning Engineer in NYC. You will design, prototype, and deploy ML systems powering autonomous permitting workflows, handling documents, insights, and end-to-end ML lifecycle.

You will work on retrieval-augmented pipelines, regression and classification tasks, and scalable backend ML infrastructure, collaborating across teams in a fast-paced startup environment.