Senior Full-Stack Python / AI /LLM Engineer

What we're looking for

• 7+ years of software development experience, with demonstrated experience building production systems.
• Strong experience with Python and backend software development.
• Experience building Python-based document processing pipelines, including parsing, transformation, and metadata extraction.
• Hands-on experience integrating and orchestrating Large Language Models (LLMs) within production applications.
• Experience with prompt engineering, including designing, tuning, and evaluating prompts for information extraction, classification, and document processing workflows.
• Experience building web applications and REST APIs.
• Experience developing AI-powered applications using LLMs.
• Familiarity with XML, XHTML, and data transformation pipelines.
• Strong problem-solving skills and comfort working with ambiguity in early-stage products.
• Excellent communication and collaboration skills.

Projects

You will join a small engineering team of 3–5 developers working on an AI-powered web application for a financial services client.The project focuses on automating XBRL tagging for tailored shareholder reports (TSRs) used by investment funds. The application uses Large Language Models (LLMs) to intelligently identify and tag financial data, including metadata that may not be directly visible in the document text.The team is currently taking an existing proof-of-concept toward a production-grade platform, with a target of reducing manual tagging efforts from hours to minutes while meeting all regulatory, technical, and business requirements.This is an early-stage product, giving the team the opportunity to contribute to architecture, engineering standards, AI integration, and the evolution of the platform as it moves into production.

What you'll do

• Drive the production hardening of the current proof-of-concept, including code quality, performance optimization, scalability, and reliability improvements.
• Establish foundational infrastructure and architectural patterns, including pipeline architecture, logging, configuration management, and error handling.
• Build and maintain Python-based backend services and REST APIs supporting the AI tagging workflow.
• Develop and evolve the web user interface, ensuring usability and alignment with engineering standards.
• Build document processing pipelines for structured and semi-structured documents, including parsing, transformation, and metadata extraction.
• Work with XML and XHTML processing to handle input data and generate compliant XBRL packages.
• Integrate and orchestrate Large Language Models within production applications, including prompt engineering, workflow orchestration, error handling, and result evaluation.
• Collaborate with the R&D team to understand AI tagging improvements and translate them into engineering requirements.
• Participate in code reviews, architecture discussions, technical design, and production support.
• Work closely with cross-functional teams to troubleshoot issues and continuously improve the platform.

Success in this role will be measured by the ability to help transition the existing proof-of-concept into a reliable, scalable production platform while improving performance and significantly reducing manual tagging effort.

Benefits

• Comprehensive medical, dental, vision, and life insurance
• Mental health support
• Savings Fund & Corporate Retirement Plan
• Paid time off, vacation bonus, and Christmas bonus
• Career development, certifications, and continuous learning
• TotalPass wellness program
• Collaborative culture with internal events and technical communities
• Opportunity to work on innovative global projects with cutting-edge technologies

Nice to have

Experience with XBRL, financial compliance, regulatory reporting, or financial data processing.Knowledge of investment company operations and SEC filing requirements.Familiarity with Retrieval Augmented Generation (RAG), embeddings, vector databases, or semantic search.Familiarity with modern web frameworks and full-stack development, particularly React, TypeScript, JavaScript, FastAPI, or Flask.Experience with LLM platforms or frameworks such as OpenAI, Azure OpenAI, Anthropic, LangChain, LangGraph, or LlamaIndex.Experience scaling systems and performing performance optimization.Background in document intelligence, NLP, information extraction, or classification systems.Experience in financial services, investment management, or regulatory technology.