VBP Careers

Description

The AI Integration Engineer is responsible for integrating data from multiple sources, automating workflows, and developing AI-driven solutions using Python, Google Cloud, and modern LLM technologies. The role focuses on preparing organizational data for AI applications, building backend services when needed, and enabling future RAG and agentic capabilities. 

Scope of Work 

Data Integration and Cloud Automation   

• Collect and consolidate data from platforms such as HubSpot, Salesforce, internal documents, spreadsheets, and other data sources
• Build automated data pipelines into Google BigQuery or other internal repositories
• Develop Python scripts for workflow automation
• Use Google Cloud services such as Cloud Functions, Cloud Run, Cloud Storage, Cloud Scheduler, and IAM

AI Preparation and RAG Foundations 

• Clean, structure, and organize data for AI projects
• Generate embeddings and set up vector search for semantic retrieval
• Prepare datasets for future RAG and agentic workflows

Backend and API Development 

• Develop internal APIs or microservices using FastAPI, Flask, or Node.js
• Deploy backend services on Cloud Run or Cloud Functions
• Implement secure API interactions with internal systems and external integrations

Responsibilities 

AI and Data Integration 

• Build ingestion pipelines from various data sources
• Clean and transform data using Python and Pandas
• Normalize structured and unstructured data for AI use
• Implement vector indexing and similarity search using OpenAI, Vertex AI, or other embedding models

Cloud Automation 

• Implement workflows using Cloud Functions, Cloud Run, Cloud Scheduler, and Pub/Sub
• Manage data storage and retrieval through BigQuery and Cloud Storage
• Configure service accounts, IAM roles, and environment variables

Backend Engineering 

• Develop and maintain internal services and APIs
• Integrate backend functions with AI models and automation workflows
• Implement authentication using OAuth2, JWT, or Google Identity

AI Search and RAG Foundations 

• Build semantic search layers across company data
• Prepare pipelines for Retrieval-Augmented Generation
• Assist in prototyping agentic workflows, such as document processors and AI assistants

Documentation and Code Quality 

• Write clean and maintainable code
• Maintain documentation for pipelines, APIs, and automation workflows
• Implement basic testing for reliability

Major Requirements: 

• Bachelor’s degree in Computer Science, Engineering, or related field
• 3+ years in a technical role involving backend, data engineering, automation, or AI
• Strong Python skills, including Pandas
• Experience with Google Cloud Platform
• Experience integrating data from APIs, files, documents, and other data sources
• Solid understanding of SQL and cloud data warehouses such as BigQuery
• Familiarity with LLM APIs such as OpenAI or Vertex AI
• Experience with FastAPI, Flask, or Node.js
• Knowledge of vector databases and semantic search
• Familiarity with Git, CI/CD, and Docker
• Understanding of agentic workflows or orchestration tools
• Strong problem-solving skills
• Ability to work independently and learn quickly
• Effective communication and collaboration 

• 500K per incident HMO coverage + Dental & Optical Benefits 
• 2 weeks of Christmas vacation
• Fixed Schedule of Mon-Fri from 7 AM to 4 PM
• Solid professional & development training programs
• 25K Educational Assistance
• Interest-free company loans