Company DescriptionNOF1 builds intelligence and data infrastructure for healthcare. Our platform helps payers and providers digitize, analyze, refine, and operationalize clinical, prior authorization, reimbursement, and payment policies. Today, much of healthcare policy work is still manual, fragmented, and difficult to translate into operational systems. NOF1 turns complex policy documents and healthcare rules into structured, searchable, comparable, and actionable data. We embed this intelligence directly into workflows so healthcare organizations can make faster, more consistent, transparent, and data-driven decisions.Our work sits at the intersection of healthcare, AI, data engineering, and operations. Joining NOF1 means building tools that directly influence real-world healthcare decisions, improve administrative efficiency, and support better clinical and financial outcomes at scale.Role DescriptionAs an AI Software Engineer at NOF1, you will design, build, and optimize the data and AI systems that power our policy intelligence platform. You will work across the full stack of applied AI: collecting and processing healthcare policy data, transforming unstructured documents into structured datasets, and building AI-powered analytics that help users understand variation, gaps, and opportunities across the healthcare market.Your work will focus on two core areas:1. Data collection and data engineeringYou will build and maintain robust pipelines for collecting, normalizing, and monitoring healthcare policy data from a wide range of public and semi-structured sources. This includes advanced web scraping, browser automation, distributed data processing, document parsing, and data quality workflows.Example work may include:Building Playwright-based crawlers for payer, vendor, and CMS policy sourcesDesigning resilient scraping systems that handle dynamic websites, authentication flows, rate limits, and document changesCreating pipelines to extract, normalize, deduplicate, and version policy documentsImproving data reliability, observability, and freshness across large-scale healthcare datasets2. AI-powered analytics and structured intelligenceYou will develop AI systems that extract meaning from complex clinical and reimbursement policy documents. This includes using LLMs, embeddings, clustering, retrieval, and classification techniques to convert unstructured policy text into structured insights.Example work may include:Using LLMs to summarize policies, extract criteria, identify services, and structure clinical rulesBuilding embedding-based similarity and clustering systems across payer policiesCreating analytics that identify coverage variation, policy gaps, reimbursement differences, and operational opportunitiesDesigning evaluation workflows to improve model accuracy, consistency, and reliabilityWorking with structured text datasets to support search, comparison, benchmarking, and decision-support use casesQualifications — RequiredStrong foundation in computer science, including data structures, algorithms, system design, and software engineering best practicesProficiency in PythonExperience building with modern LLM APIs, including OpenAI, Anthropic, Gemini, or similar modelsExperience with chat completion, structured outputs, tool/function calling, embeddings, and retrieval-based workflowsHands-on experience with NLP, especially extracting structure, meaning, entities, or relationships from unstructured textExperience with advanced web scraping and browser automation tools such as Playwright, Selenium, BeautifulSoup, Scrapy, or similar frameworksExperience building and deploying production systems, including APIs, cloud services, databases, CI/CD, and version controlAbility to work with messy real-world data and build systems that are reliable, observable, and maintainableStrong communication skills and the ability to explain technical concepts clearly to clinical, operational, and business stakeholdersBachelor’s degree or advanced degree in Computer Science, Engineering, or a related technical field, or equivalent practical experienceQualifications — PreferredExperience working with healthcare data, payer/provider workflows, clinical policy, prior authorization, reimbursement policy, or claims dataFamiliarity with healthcare coding systems such as CPT, HCPCS, ICD-10, NDC, DRG, or revenue codesExperience with search, ranking, embeddings, vector databases, or knowledge graph systemsExperience designing evaluation frameworks for LLM outputs, including accuracy, consistency, hallucination detection, and human review workflowsExperience with distributed systems, job queues, batch processing, or large-scale data pipelinesFamiliarity with data privacy, HIPAA, SOC 2, or other healthcare regulatory considerationsComfort working in an early-stage startup environment where priorities move quickly and engineers own meaningful product areas end to end