Remote Senior Backend Engineer
工作从任何地方在拉塔姆的工作时间表：EST 关于珍珠人才珍珠与全球最优秀的1%候选人合作，并将他们联系到美国和欧盟的最佳初创公司。我们的客户总共筹集了超过50亿美元，并且得到了 OpenAI,a16z 和 Founders Fund 等公司的支持。了解我们为什么存在，我们相信什么以及我们正在为谁构建：在这里查看有关客户的一家种健康数据公司正在建立支付者政策数据中心来源，并在覆盖决策背后寻找一名高级后端工程师拥有其数据基础设施。该公司从100多家保险人那里收集和构建超过10万个医疗政策，使用 AI 将复杂的支付者规则转化为客户可搜索数据。它得到了医疗保健加速器和国家卫生研究院的支持，最近签署了一项商业合作伙伴关系，现在正在扩大其应用 AI 系统。角色日到日，你将扩展网络剪辑平台，建立 LLM 工作流程，从政策文本中拉出医疗代码和覆盖规则，并提高剪辑员的工作和部署的可靠性。作为技术领导，你将审查代码并做出兼职和离岸工程师的建筑决策，而不直接管理人员。成功意味着可靠的选工作，自动化测试和部署以及足够准确的结构数据让客户可以采取行动。核心责任网络选基础设施 · 建立和扩展开发从100多个付款人收集政策数据的选平台 · 在不减少数据精度的情况下提高选器的可靠性和吞吐量 · 从存储到摄入中拥有选管道 LLM 数据规范化 · 构建 LLM 的工作流程将未结构化的政策文本转换为结构化，可搜索的记录 · 从政策语言状态下输入相关医疗代码 (CPT,ICD-10) · 分类程序覆盖 （涵盖或不受纳税）· 建立评估和测试带来衡量和跟踪输出精度 CI/CD 和系统可靠性 ·构建和维护 CI/CD 管道用于测试和部署碎机工作 ·监控工作故障，诊断根本原因和船只修复 ·审查兼职和离岸工程师的拉动请求 ·记录建筑决策并与工程团队分享 API 和数据产品 ·设计和维护服务于正常化政策数据的 API
查看英文原文
Work From Anywhere in LATAM
Work Schedule: EST | Full overlap with US Eastern business hours
About Pearl Talent
Pearl works with the top 1% of candidates from around the world and connects them with the best startups in the US and EU. Our clients have raised over $5B in aggregate and are backed by companies like OpenAI, a16z, and Founders Fund.
Hear why we exist, what we believe in, and who we’re building for: Watch here
About the Client
A seed-stage healthcare data company is building the central source of payer policy data behind coverage decisions, and is looking for a Senior Backend Engineer to own its data infrastructure end to end.
The company collects and structures more than 100,000 medical policies from over 100 insurance payers, using AI to turn complex payer rules into searchable data for customers. It is backed by healthcare accelerators and the National Institutes of Health, recently signed a commercial partnership, and is now scaling its applied AI systems.
About the Role
Day to day, you will scale the web scraping platform, build LLM workflows that pull medical codes and coverage rules out of policy text, and improve the reliability of scraper jobs and deployments. As technical lead, you will review code and make architectural decisions for part-time and offshore engineers, without managing people directly. Success means reliable scraper jobs, automated testing and deployment, and structured data accurate enough for customers to act on.
Core Responsibilities
Web Scraping Infrastructure
- Build and scale the platform used to develop scrapers that collect policy data from 100+ payers
- Improve scraper reliability and throughput without reducing data accuracy
- Own the scraper pipeline from ingestion through storage
LLM Data Normalization
- Build LLM workflows that convert unstructured policy text into structured, searchable records
- Infer and tag related medical codes (CPT, ICD-10) from policy language
- Classify procedure coverage status (covered or not covered) by payer
- Build evaluation and testing harnesses to measure and track output accuracy
CI/CD and System Reliability
- Build and maintain CI/CD pipelines for testing and deploying scraper jobs
- Monitor job failures, diagnose root causes, and ship fixes
- Review pull requests from part-time and offshore engineers
- Document architectural decisions and share them with the engineering team
APIs and Data Product
- Design and maintain APIs that serve normalized policy data to customers
- Support the Snowflake-based data product used by customers
- Join occasional customer calls to understand feature requirements
Requirements
Must-Have
- 5+ years of backend engineering experience building production systems in Python
- Production experience with SQL and PostgreSQL for storing and querying large datasets
- Experience building pipelines that ingest, clean, and normalize messy or unstructured data
- Hands-on experience deploying and running backend services on AWS, GCP, or Azure
- Experience reviewing code and owning architectural decisions on a shared codebase
- English at C1 (CEFR) for daily video calls and technical discussions with US-based founders
Nice-to-Have
- Experience building LLM-based extraction or classification with evaluation harnesses (OpenAI, Anthropic, LangChain, or similar)
- Web scraping at scale with Scrapy, Playwright, or similar frameworks
- Experience with RAG (Retrieval-Augmented Generation) pipelines
- Hands-on use of Terraform, FastAPI, or Snowflake
- Exposure to healthcare payer policy data, medical coding (CPT, ICD-10), or prior authorization
Benefits
· Competitive Salary: Based on experience and skills
- Remote Work: Fully remote—work from anywhere
- Team Incentives: Recognition for maintaining 100% CRM hygiene and on-time reporting
- Generous PTO: In accordance with company policy
- Health Coverage for PH-based talents: HMO coverage after 3 months for full-time employees
- Direct Mentorship: Guidance from international industry experts
- Learning & Development: Ongoing access to resources for professional growth
- Global Networking: Connect with professionals worldwide
Our Recruitment Process
- Application
- Screening
- Skills Assessment
- Topgrading Interview
- Client Interview
- Job Offer
- Client Onboarding
Ready to Join Us?
If you’re empathetic, organized, and passionate about improving patient experiences through operational excellence, this role is for you. Apply now to help make specialized healthcare more accessible to patients across the U.S.
Originally posted on Himalayas