Founding Engineer

Policybot is building the data infrastructure that powers how healthcare decisions are made. We catalog, normalize and structure complex payer policies to enable clearer coverage decisions, faster patient access, and smarter product strategy. Policybot’s data powers thousands of automated workflows every day.

Our small team is made up of veterans from companies like Oscar Health and Teladoc to make policies easy to use. We’re now focused on scaling our applied AI systems to turn overly complex payer rules into actionable next steps for our customers.

Policybot is on a mission to make health insurer policy data accessible, structured, and executable. As a founding engineer, you’ll own core systems end-to-end: ingesting messy policy data, structuring it, layering AI systems on top, and creating a platform that becomes the canonical source of truth for healthcare policy intelligence.

You’ll work directly with the founders to design, build, and ship critical parts of our product — spanning full-stack and AI engineering. This is a unique opportunity to get hands-on startup experience, learn at a rapid pace, and make a meaningful impact on healthcare technology.

Key responsibilities may include:

• Design ingestion pipelines that convert messy, unstructured payer policies into structured, queryable objects

• Define data schemas that evolve without breaking downstream consumers, and enforce data quality as a top concern

• Leverage AI to scale the data ingestion pipeline to cover hundreds of health insurers

• Build pipelines for auditability, traceability, and explainability

• Build and refine LLM-powered data pipelines that extract and and structure data elements from raw text to make policy data more useful

• Develop systems for evaluating and benchmarking LLM-driven features, including evaluation harnesses, QA workflows, and human validation loops

• Make improvements in our search capabilities by designing and implementing RAG (Retrieval-Augmented Generation) pipelines over healthcare policy documents; experiment with embeddings, vector databases, and fine-tuning strategies
  

• Rapidly build prototypes, quickly determine what works and what doesn’t, , convert what works to production systems and trash the rest

• Navigate ambiguous environments by continuously asking questions until you understand what problem you’re solving

• Recognize that 80% of the value is data quality and usability over shiny features, and make tradeoffs accordingly

• Demonstrate end-to-end product ownership to ensure new tech is fully integrated into the company and product, ownership doesn’t stop when code hits prod

• Leverage AI to scale your work and improve the entire organization’s efficiency
  

• 5+ years experience building data-heavy backend systems (or equivalent track record)

• A track record of working with data pipelines and data-driven software products

• Deep comfort with Python, SQL, Postgres, and modern cloud infrastructure (AWS preferred)

• Experience building AI-native products, such as LLMs, RAG, embeddings, prompt engineering, hallucination mitigation, data labeling, evals, and monitoring

• Are product-oriented and able to evaluate the tradeoff of technical changes against business value

• Fluency in designing and evolving data models, schemas and APIs for long-term maintainability

• Proven ability to take ambiguous problems, define the requirements, map the ideal architecture, and execute end-to-end

• Experience designing and building backend infrastructure for scalability

• Able to operate manage, plan, and run projects independently

• Able to thrive in a fast-paced, ambiguous environment
  

• Exposure to healthcare, payer/provider data, or health tech

• Prior exposure to startups, research teams, or high-paced environments

• Willingness to dive into new tools, frameworks, and AI systems quickly

• Experienced in front-end development (TypeScript/React)

• Prior experience developing high throughput applications on FastAPI

• Experienced working with data warehouses (eg, Snowflake)

• Exposure to Infrastructure‑as‑Code (e.g., Terraform) and container orchestration

• Be part of a small, ambitious team where you’ll shape the architecture, culture, and velocity of the engineering org from day one.

• You’ll work directly with founders to solve some of the hardest data problems in healthcare.

• Experiment with cutting-edge AI tools and apply them to hard problems

• You’ll own systems that become the backbone of a new category of data infrastructure in healthcare

• Founding equity

• Health insurance

• Pre-tax commuter and dependent care benefits

• 401K

• Learning stipend

• Unlimited PTO

Have questions? Email us at [email protected].