AI Engineer

About Us At Metaprise, we’re building the world’s first Financial Operating System — an AI Agent–powered platform that unifies Accounts Receivable, Accounts Payable, Contract Management, SmartFlow Automation, and Cash Management into a single intelligent hub. We help enterprises eliminate operational gaps between financial tools, giving them total control over data flow and cash flow. Backed by real customers in the US and global expansion momentum, we’re scaling fast and looking for builders who thrive in high-growth, high-impact environments. Requirements

Bachelor's degree or above in Computer Science, AI, or related fields

2-3 years of Python development experience with solid machine learning foundation

Deep understanding of vector retrieval and embedding model technologies

Proficient in vector databases (Pinecone, Chroma, Weaviate) and retrieval optimization tools

Familiar with OCR technology, experienced in multimodal model processing for documents, images, data preprocessing and feature extraction

Experience in designing RAG (Retrieval-Augmented Generation) solutions

Proficient in PyTorch/TensorFlow frameworks with hands-on experience in Hugging Face, LangChain/LangGraph tools

Strong English reading and writing skills, excellent learning ability

Good communication and collaboration skills

Responsibilities

AI Agent Development & Integration:

Develop intelligent financial agents using LangChain, LangGraph and related frameworks

Design and implement multi-agent collaborative systems for complex financial workflows

Build intelligent AR/AP automation agents for accounts receivable/payable processing

Develop smart report generation agents for automated financial analysis and data visualization

RAG System Design & Vector Retrieval:

Design and implement RAG (Retrieval-Augmented Generation) systems for financial knowledge bases

Build vector databases for efficient document retrieval and semantic search

Develop embedding model optimization solutions to improve retrieval accuracy and response speed

Integrate multimodal data processing to support various formats including financial documents, invoices, and reports

Document Processing & Multimodal AI:

Integrate OCR technology for intelligent recognition of financial receipts and documents

Develop multimodal model processing solutions for documents, images, tables and mixed data types

Establish document preprocessing and feature extraction pipelines to improve data quality

Integrate with mainstream ERP systems through APIs for real-time data synchronization

AI Model Optimization & Training:

Conduct model fine-tuning and training using PyTorch/TensorFlow frameworks

Utilize Hugging Face ecosystem for model selection and optimization

Optimize agent response quality through Prompt Engineering techniques

Establish model performance evaluation systems for continuous AI system improvement

Ensure all AI systems comply with US financial regulations (SOX, GAAP, etc.)

Nice to Have

Fintech industry experience

Cloud platform deployment experience (AWS/GCP/Azure)

Large-scale vector retrieval system optimization experience