Data Engineer - LLM Applications

Data Engineer - LLM Applications

A growing organization is building an enterprise data platform to support research, analytics, and operational workflows. The team works across data engineering and applied AI, with a focus on creating reliable, governed, and auditable ways for users to interact with complex datasets.

The work combines large-scale data engineering, data platforms, and AI-enabled applications, with a strong emphasis on reliability, data quality, security, and production readiness.

We are seeking a Data Engineer to help build and operate modern data platforms and AI-enabled data solutions.

This role goes beyond traditional ETL. You will design and maintain data pipelines while contributing to AI-driven data access systems that allow users to interact with enterprise datasets through natural-language interfaces and structured queries.

You will work closely with engineering and AI/ML teams to connect enterprise data systems with modern AI capabilities that support analytics, discovery, and decision-making.

• Design and maintain scalable, production-grade data pipelines.
• Build and optimize data models for analytical and AI-driven workloads.
• Develop high-quality Python and SQL for data transformation, standardization, reconciliation, and validation.
• Collaborate with AI/ML engineers on AI-enabled data access solutions.
• Contribute to frameworks that connect enterprise data with LLM-based applications.
• Work with external data providers and internal stakeholders.
• Implement monitoring, testing, validation, and governance for data and AI workflows.
• Document data architectures, pipelines, and technical processes.
• Support troubleshooting and optimization of production data systems.
• Strong foundation in data engineering and data modeling.
• Proficiency in SQL, Python, Java, and Spark.
• Hands-on experience with modern cloud data platforms such as Databricks and/or Snowflake.
• Experience with software development, data integration, and production-grade data reconciliation.
• Experience working with complex, sensitive, or regulated datasets is preferred.
• Experience with, or strong interest in, LLM-powered enterprise applications.
• Familiarity with GraphQL, APIs, or other structured data access technologies.
• Strong documentation, communication, and problem-solving skills.
• Bachelor’s degree or higher in Computer Science, Data Science, Information Technology, Software Engineering, or a related field.
• Approximately 1–3+ years of experience in software or data engineering.
• Authorization to work in the United States without current or future sponsorship.
• Ability to work a hybrid schedule in the applicable office region.
• Flexibility to support production systems outside standard business hours when necessary.

For immediate consideration, please email a resume to Kenny at [email protected]. A cover letter highlighting recent experience, post-graduate research contributions, GitHub, personal projects, and professional references, if applicable, is strongly preferred. Must be local to Boston and able to come to our office in Downtown Boston for an introductory meeting to be considered.

Salary range: $140-170,000 + Discretionary Bonus.