What You’ll Do

• Take an AI-powered document tagging solution from proof-of-concept to production, improving code quality, performance, and reliability
• Establish core infrastructure and architectural patterns: pipeline architecture, logging, configuration management, and error handling
• Develop and evolve the web user interface with a focus on usability and engineering standards
• Build and maintain backend services and APIs that support the tagging workflow
• Process XHTML and XML data, integrating with financial reporting platforms to generate compliant XBRL packages
• Partner with the R&D team to translate AI tagging improvements into engineering requirements
• Take part in code reviews, architecture discussions, and production support

What You’ll Bring

• 7+ years of software development experience building production systems
• Hands-on experience with Python-based document processing pipelines (parsing, transformation, and metadata extraction from structured and semi-structured documents)
• Experience building AI-powered applications and orchestrating LLMs in production, including error handling and result evaluation
• Prompt engineering skills: designing, tuning, and evaluating prompts for extraction, classification, and document workflows
• Experience building web applications and REST APIs
• Familiarity with XML, XHTML, and data transformation pipelines
• Strong problem-solving skills and comfort with ambiguity in early-stage products
• Excellent communication and collaboration with cross-functional teams
• Nice to have: XBRL, financial compliance, or regulatory reporting experience; knowledge of investment company operations and SEC filings; RAG; modern web frameworks and full-stack development; scaling systems and performance optimization