Job Summary: We’re building a lightweight MVP for an AI-powered tool that helps industrial companies make sense of complex regulatory documents. Your job: build the backend engine that ingests long, messy documents and produces clean, structured summaries with LLM assistance. This is a fully async role — no meetings, no Slack — with clear deliverables and a technical PM managing the timeline. Key Responsibilities: Processes PDFs and semi-structured files Extracts relevant data fields and interprets them via LLM Returns structured JSON outputs with scoring or flagging logic Supports a simple question-answering interface for document insights Helps QA your output on a test set of 50+ samples Required Skills & Qualifications: ✅ Strong Python and LLM API experience (OpenAI, Claude, Gemini) ✅ Familiarity with LangChain or other document processing tools ✅ Comfort handling real-world PDFs with inconsistent formatting ✅ Experience outputting structured JSON from AI pipelines ✅ Self-managed, async workflow (GitHub + Notion) Nice to Have
Keyword: Data Cleaning
Price: $10.0
AI App Development AI Development Python Artificial Intelligence Natural Language Processing
Who We Are A leading M&A advisory firm in the senior housing and care space is seeking a financial analyst to support our investment sales team. We’ve built a strong reputation on transparency, attention to detail, and relentless follow-through—and we need someone w...
View JobI need a before and after image. The before is a standalone Data Lake with traditional sources. The after is a standalone Data Lake with integration to 3rd party data sources (ie clean room), but I need to edit those to include Agentic Workflows, Multi-party fraud cross...
View JobWe are seeking a skilled database administrator to assist with the transition of our PostgreSQL database from Amazon Web Services (AWS) to Google Cloud Platform (GCP). The ideal candidate will have experience in database migration, ensuring a smooth transfer with minima...
View Job