Python Developer For Healthcare AI and RAG

Egs Info-tech; United States; Remote; USD 130,000 - 180,000; Full time

Job summary

Egs Info-tech in United States is seeking a data engineer to carefully work with healthcare data, improve the existing Python pipeline, and build RAG features that ground oncology reports in reliable clinical evidence.

The role focuses on Python data pipelines, converting healthcare data into structured summaries, and retrieving clinical evidence from trusted sources while writing SQL queries and validation logic. You will also add tests and help make AI-generated reports safer and more reliable.

Qualifications

• Strong Python experience.
• SQL experience.
• Experience with RAG, embeddings, vector databases, or document retrieval.
• Ability to work with JSON data.
• Good debugging and testing skills.
• Careful attention to data accuracy.

Responsibilities

• Work on Python data pipelines.
• Convert healthcare data into structured summaries.
• Build and improve RAG workflows.
• Retrieve relevant clinical evidence from trusted sources.
• Write SQL queries and data validation logic.
• Improve clinical report generation.
• Add tests to make outputs are accurate.
• Help make AI-generated reports safer and more reliable

Skills

Python

SQL

RAG/Embeddings

JSON

Testing

Tools

DuckDB

Pydantic

Job description

Summary

We need someone who can work carefully with healthcare data, improve the existing Python pipeline, and build RAG features that ground oncology reports in reliable clinical evidence.

Responsibilities

• Work on Python data pipelines.
• Convert healthcare data into structured summaries.
• Build and improve RAG workflows.
• Retrieve relevant clinical evidence from trusted sources.
• Write SQL queries and data validation logic.
• Improve clinical report generation.
• Add tests to make sure outputs are accurate.
• Help make AI-generated reports safer and more reliable

Required Skills

• Strong Python experience.
• SQL experience.
• Experience with RAG, embeddings, vector databases, or document retrieval.
• Ability to work with JSON data.
• Good debugging and testing skills.
• Careful attention to data accuracy.

Nice to Have

• Healthcare or FHIR experience.
• Oncology knowledge.
• Experience with LLMs or AI tools.
• DuckDB, Pydantic, or document generation experience.
• Familiarity with clinical guidelines, medical literature, or trial matching.