Project Summary

We're seeking an expert LangChain developer to build an intelligent AI assistant that automates the processing and answering of complex medical claims and policy inquiries for a FinTech platform serving healthcare providers in Singapore. The goal is to enhance efficiency and accuracy in handling common financial queries.

Detailed Requirements

We need an expert developer with a deep understanding of LangChain and natural language processing to design and implement a robust AI assistant. Key requirements include:

• LangChain Expertise: Proven experience in building production-ready applications with LangChain, including custom tools, agents, and chain orchestration.

• Python Proficiency: Strong programming skills in Python for backend development and API integration.

• NLP & LLM Understanding: Solid grasp of NLP concepts, prompt engineering, and working with various Large Language Models.

• RAG Implementation: Ability to design and implement a Retrieval Augmented Generation (RAG) system for accessing and synthesizing information from diverse medical and financial documents (e.g., policy documents, Explanation of Benefits (EOBs), claims forms).

• Domain Knowledge (Preferred): Familiarity with medical claims terminology (CPT codes, ICD-10, claim statuses) and FinTech data structures related to healthcare billing is a significant advantage.

• API Integration: Experience integrating with internal/external APIs for data lookup (e.g., dummy patient records, policy databases).

• Architecture & Scalability: Ability to propose and implement a scalable, maintainable, and secure architecture for the AI assistant.

• Testing: Commitment to writing comprehensive unit and integration tests.

• Documentation: Provide clear, concise, and thorough documentation for code, setup, and usage.

Deliverables

Upon successful completion of the project, the freelancer will deliver the following:

• Fully Functional LangChain AI Assistant: A complete Python application demonstrating the AI assistant's core capabilities, including:

• An agent capable of understanding medical claims and policy inquiries.

• A robust RAG system integrated with a provided knowledge base (e.g., sample policy documents, medical code lists).

• The ability to generate accurate, context-aware responses based on ingested data.

• API Endpoints: Well-documented API endpoints (e.g., using FastAPI or Flask) for submitting user queries and receiving AI-generated responses.

• Comprehensive Test Suite: A suite of unit and integration tests ensuring the reliability and correctness of the AI assistant's functions.

• Deployment Guide: Instructions or a basic setup script for deploying the application to a cloud environment (e.g., AWS, Azure, GCP).

• Technical Documentation: Detailed documentation covering the architectural design, code structure, setup instructions, and usage guidelines.

Timeline & Budget

• Expected Timeline: 1 Month

• Budget Range: $1500 - $3000