Datafold seeks senior engineer to build AI-powered database migration tool

Datafold is expanding its AI capabilities with a new role focused on developing their Migration Agent, a tool that automates database migrations using LLMs and proprietary diffing technology. This position represents a growing trend of startups applying AI to specialized data engineering problems, potentially disrupting traditional migration processes that typically require extensive manual work and specialized consultants.

The opportunity: Datafold is hiring a senior software engineer to lead development of their AI-powered data migration tool that promises to reduce migration timelines by 5-10x.

• The role focuses on building the Datafold Migration Agent (DMA), which combines large language models with data diffing technology to automate SQL dialect translation and data reconciliation.
• The successful candidate will design backend systems, collaborate with early customers, and make strategic technical decisions to ensure the product scales effectively.

Company context: Datafold is a Series A startup focused on data quality and observability tools for data engineers.

• Founded in 2020, the company has raised $22M from prominent investors including Y Combinator, NEA, and Amplify Partners.
• The 24-person team serves clients like Disney, FanDuel, Perplexity, Patreon, and Thumbtack while operating fully remote across the US and EU.

Technical requirements: The position requires significant backend engineering experience and specific technical capabilities.

• Candidates need 5+ years of software engineering experience with strong backend skills, with Python proficiency being mandatory.
• Experience building with large language models and JavaScript/TypeScript knowledge are considered advantages but not requirements.

Strategic focus: Datafold’s core philosophy centers on preventing data quality issues before they reach production environments.

• The company believes data quality results from effective engineering workflows rather than reactive testing.
• Their approach emphasizes addressing quality issues during the development phase and leveraging metadata to improve data engineering processes.