Multimodal AI Engineer - Engineering Drawings

Pyramid It Consulting; United States; Remote; USD 120,000 - 180,000; Full time

Job summary

Pyramid It Consulting is seeking a Computer Vision AI Specialist / Multimodal AI Engineer for work in the United States. The role focuses on applying computer vision to engineering drawings, OCR and symbol detection, and building AI applications in Python.

You will work with RAG, embeddings, vector databases and drawing retrieval to support enterprise workflows. Required experience with AWS Bedrock, AgentCore, Terraform and Databricks, and designing multi-agent MCP architectures.

Qualifications

• Experience applying computer vision to engineering drawings.
• Expertise in OCR, symbol detection and Vision Language Models (VLMs).
• Strong Python AI application development.
• Familiarity with RAG, embeddings and vector databases.
• Experience with drawing retrieval workflows.

Skills

Computer vision

Multimodal AI

Symbol detection

OCR

Vision Language Models

Python

RAG

Embeddings

Vector databases

Drawing retrieval

Tools

AWS Bedrock

AgentCore

Terraform

Databricks

Job description

Pyramid It Consulting is seeking a Computer Vision AI Specialist / Multimodal AI Engineer for work in the United States. The role focuses on applying computer vision to engineering drawings, OCR and symbol detection, and building AI applications in Python.

You will work with RAG, embeddings, vector databases and drawing retrieval to support enterprise workflows. Required experience with AWS Bedrock, AgentCore, Terraform and Databricks, and designing multi-agent MCP architectures.