Software Engineer (All Levels)

Codes Health•New York, NY

3d•Onsite

About The Position

Codes Health is revolutionizing the retrieval of medical records for plaintiff litigation, a process that currently takes 30-50 days due to manual efforts like faxing, calling, and navigating provider portals. Codes Health aims to reduce this to approximately 12 days by building an agentic layer that learns and adapts to the complexities of accessing information from diverse healthcare providers. This system is designed to ingest data from various sources, including fax, email, web portals, and physical mail, and process large volumes of records (averaging 300 pages, sometimes up to 30,000) to extract relevant information. The company also addresses challenges in matching patients and facilities across complex provider networks. The engineering team works across automating the retrieval pipeline, developing the customer-facing product for law firms, and implementing applied AI. Engineers are expected to contribute to all areas, shifting focus as company goals evolve, and to engage directly with customers and data.

Requirements

Shipped features start to finish in production and want to own outcomes.
Go deep on the domain: the data systems and the workflows our agents run.
Explored LLMs and are excited about turning them into reliable systems.
Want to talk to users directly and ship off their feedback.
Excited to apply real engineering rigor to a messy, economically valuable problem.
TypeScript and React on the frontend.
Python and FastAPI on the backend.

Responsibilities

Building agentic systems that run end to end across fax, email, web portals, and physical mail, where each document type triggers a different workflow.
Processing records that average 300 pages, sometimes hit 30,000, and run roughly 70% duplicate, and still surfacing what matters to a case.
Matching patients and facilities across messy provider networks, where a single system like NYU Langone is 340+ care locations with no clean way to match them.
Automating the retrieval pipeline.
Developing the customer-facing product law firms use to request and view records.
Implementing applied AI threaded through both the pipeline and the customer-facing product.
Shipping customer-facing product.
Deep diving on the pipeline.
Staying close to both the customer and the data.