Agentic AI & LLM Engineer for SEC.gov Research Intelligence Platform

We are looking for an experienced Agentic AI and LLM Engineer to build an intelligent research and automation platform using publicly available filings and documents from SEC.gov. The system will collect, process, analyze, and structure financial information from SEC filings such as 10-K, 10-Q, 8-K, registration statements, prospectuses, exhibits, and asset-backed securities reports. The ideal candidate should have experience with LLM-powered research systems, document intelligence, financial data extraction, retrieval-augmented generation, and production-grade automation. Project Responsibilities Build automated pipelines to discover and download filings from SEC.gov and EDGAR. Process SEC HTML, XML, XBRL, PDF, and text documents. Extract financial metrics, tables, disclosures, risk factors, transaction details, and other structured information. Develop AI agents that can research companies, securities, trusts, and financial transactions. Build RAG pipelines for searching and answering questions across large collections of SEC filings. Generate research reports with source references and filing-level citations. Create workflows for comparing filings across companies, reporting periods, or securities. Implement structured outputs using predefined schemas. Develop validation and reconciliation checks to reduce extraction errors and hallucinations. Integrate the solution with APIs, databases, dashboards, or internal applications. Document the architecture, extraction logic, and deployment process. Example Use Cases Analyze quarterly and annual company filings. Extract KPIs and financial disclosures from 10-K and 10-Q reports. Track changes in risk factors and management commentary. Analyze asset-backed securities and trust-level performance reports. Extract payment waterfalls, triggers, delinquency metrics, losses, and credit enhancement data. Compare SEC disclosures across reporting periods. Generate cited investment or financial research summaries. Required Skills Strong Python development experience. Hands-on experience with OpenAI, Anthropic, Gemini, or open-source LLMs. Experience building agentic AI workflows using LangGraph, LangChain, CrewAI, AutoGen, or similar frameworks. Strong understanding of RAG, embeddings, vector search, hybrid retrieval, and reranking. Experience parsing SEC filings, EDGAR data, XBRL, XML, HTML, PDFs, or complex financial documents. Experience designing structured data extraction pipelines. Familiarity with financial statements and public-company filings. Experience with FastAPI, PostgreSQL, Docker, and cloud deployment. Ability to build reliable production systems rather than basic AI demonstrations. Preferred Experience Previous experience working with SEC.gov or EDGAR APIs. Experience analyzing securitizations, asset-backed securities, loan portfolios, or trust reports. Knowledge of financial metrics, accounting terminology, and regulatory disclosures. Experience with document OCR, table extraction, and data reconciliation. Familiarity with Pinecone, Qdrant, Weaviate, OpenSearch, Elasticsearch, or FAISS. Experience implementing LLM evaluations, observability, guardrails, and citation verification. Application Questions Please include the following in your proposal: Have you previously worked with SEC.gov, EDGAR, XBRL, or financial filings? Share an example of an LLM-based document intelligence or research system you have built. How would you reliably extract structured financial data from SEC filings? How would you validate LLM-generated outputs against the original filing? Which agentic AI, retrieval, and vector database technologies would you recommend? Please share your GitHub, portfolio, or a relevant project demonstration. We are looking for someone who can understand complex financial documents, design the right AI architecture, and independently deliver a reliable and scalable research intelligence platform. This may become a long-term engagement for the right candidate.