Data Engineer

Role Summary

Build and maintain the enterprise data lake, design ETL pipelines, develop ML models for forecasting, and create AI agents/MCP integrations using LLM APIs.

Experience

4+ Years

Required Skills

• Python ETL - Pandas, NumPy, data modelling, API integrations
• SQL - Complex queries, schema design, performance tuning
• GCP - BigQuery, Cloud Storage, CloudRun, Secret Manager
• Data Lake Design - Ingestion from ERP/CRM systems (NetSuite, Salesforce), schema evolution, data quality
• REST API - Development and consumption (OAuth, webhooks)
• Git & CI/CD - Version control and deployment basics

Preferred Skills

• AI Agent Development - Tool-calling agents, MCP servers, LLM APIs (Claude, Gemini, OpenAI)
• Machine Learning - Time series forecasting, predictive modelling (Prophet, XGBoost, SARIMAX)
• BI Tools - Qlik or Looker
• Orchestration - Cloud Scheduler, Airflow, or cron-based job pipelines

Key Responsibilities

• Build and maintain data lake on BigQuery - ingestion, transformation, scheduling
• Design and implement ETL pipelines (Python) across banking, ERP, and CRM sources
• Experiment with and deploy ML models for cash forecasting and business predictions
• Develop AI agents and MCP tool integrations using LLM APIs
• Ensure data quality, monitoring, and alerting across pipelines

Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.