Software Engineer - Data/AI

Software Engineer, Data/AI – Healthcare Data & AI

About the Team

RA Capital’s Data Engineering team builds the enterprise data platform that powers research, investment, and operational workflows across the firm. Beyond traditional data pipelines, we are actively developing AI-native data access patterns that enable users to interact with complex healthcare datasets through LLM-powered, governed, and auditable interfaces.

Our work sits at the intersection of healthcare data, large-scale data engineering, and applied AI, with a strong emphasis on reliability, compliance, and production readiness.

About the Role

We are seeking an early-career software engineer to help build and operate AI-enabled data platforms and intelligent data workflows for healthcare data.

This role goes beyond traditional ETL. You will build healthcare data pipelines as well as AI-driven workflows and data applications that connect large language models with enterprise data and tools. This includes developing governed data access layers where LLMs translate user intent into structured queries and building agentic workflows that retrieve information, invoke tools, orchestrate multi-step tasks, and support self-service analytics, discovery, and decision-making.

Responsibilities

• Design and maintain scalable, production-grade data pipelines for healthcare datasets, including claims and provider data.

• Build and optimize data models to support analytical and AI-driven workloads.

• Develop high-quality Python and SQL code for data standardization, reconciliation, validation, and application workflows.

• Build AI-powered data applications and agentic workflows that connect LLMs with enterprise data and internal tools, retrieve information, execute multi-step tasks, and automate data and research processes with appropriate guardrails.

• Build and improve AI-native data access frameworks, including LLM-to-SQL and LLM-to-GraphQL patterns and reusable interfaces for structured data access.

• Build backend services, APIs, and reusable software components that power data and AI applications.

• Develop evaluation and testing frameworks to measure the accuracy, reliability, and performance of LLM-powered and agentic workflows.

• Write automated tests and contribute to CI/CD, deployment, and production support for data and AI systems.

• Collaborate with AI/ML engineers, healthcare data vendors, and internal stakeholders to translate user needs into production-ready data and AI solutions.

• Implement monitoring, observability, and governance for data pipelines and AI workflows.

• Document data architectures, AI-enabled workflows, and production systems.

Key Skills and Experience

• Strong software engineering fundamentals and an interest in building production systems.

• Strong foundation in data engineering and data modeling.

• Proficiency in Python and SQL; experience with Spark and Databricks is preferred.

• Experience building or integrating APIs, services, or workflow-oriented applications.

• Hands-on experience with, or a strong interest in, LLM-powered applications, AI agents, or agentic workflows.

• Familiarity with LLM tool use, structured outputs, orchestration patterns, GraphQL, or other API-based data access methods.

• Experience working with healthcare or other regulated datasets is a plus.

• Strong communication, ownership, and collaboration skills.

Qualifications

• Bachelor’s degree or higher in Computer Science, Software Engineering, Data Science, or a related technical field, or equivalent practical experience. A master’s degree is preferred.

• Up to three years of experience in software engineering, data engineering, or a related role.

• Must be based in the Boston area and available to work a hybrid schedule from our Boston office. Relocation assistance is not provided.

• Must be authorized to work in the United States without current or future sponsorship.