Data Engineer - ML & AI

As a Data Engineer at Bachatt, you will play a crucial role in building and maintaining the enterprise data lake, designing ETL pipelines, developing ML models for forecasting, and creating AI agents/MCP integrations using LLM APIs. Your responsibilities will include: - Python ETL: Utilize Pandas, NumPy, and data modeling techniques for efficient API integrations. - SQL: Handle complex queries, schema design, and performance tuning to ensure optimal data retrieval. - GCP: Work with BigQuery, Cloud Storage, CloudRun, and Secret Manager for seamless data management. - Data Lake Design: Ingest data from ERP/CRM systems like NetSuite and Salesforce, evolve schemas, and maintain data quality. - Git & CI/CD: Implement version control and deployment basics for streamlined workflows. Additionally, you will be involved in: - AI Agent Development: Create tool-calling agents, MCP servers, and integrate with LLM APIs such as Claude, Gemini, and OpenAI. - Machine Learning: Apply techniques like time series forecasting and predictive modeling using Prophet, XGBoost, and SARIMAX. - Orchestration: Utilize Cloud Scheduler, Airflow, or cron-based job pipelines for efficient task scheduling. Your tasks will also include: - Building and maintaining the data lake on BigQuery, including data ingestion, transformation, and scheduling. - Designing and implementing ETL pipelines in Python across banking, ERP, and CRM sources. - Experimenting with and deploying ML models for cash forecasting and business predictions. - Developing AI agents and MCP tool integrations while ensuring data quality, monitoring, and alerting across pipelines. Join Bachatt to be a part of a dynamic team working towards revolutionizing the savings and investment landscape for self-employed individuals in India! As a Data Engineer at Bachatt, you will play a crucial role in building and maintaining the enterprise data lake, designing ETL pipelines, developing ML models for forecasting, and creating AI agents/MCP integrations using LLM APIs. Your responsibilities will include: - Python ETL: Utilize Pandas, NumPy, and data modeling techniques for efficient API integrations. - SQL: Handle complex queries, schema design, and performance tuning to ensure optimal data retrieval. - GCP: Work with BigQuery, Cloud Storage, CloudRun, and Secret Manager for seamless data management. - Data Lake Design: Ingest data from ERP/CRM systems like NetSuite and Salesforce, evolve schemas, and maintain data quality. - Git & CI/CD: Implement version control and deployment basics for streamlined workflows. Additionally, you will be involved in: - AI Agent Development: Create tool-calling agents, MCP servers, and integrate with LLM APIs such as Claude, Gemini, and OpenAI. - Machine Learning: Apply techniques like time series forecasting and predictive modeling using Prophet, XGBoost, and SARIMAX. - Orchestration: Utilize Cloud Scheduler, Airflow, or cron-based job pipelines for efficient task scheduling. Your tasks will also include: - Building and maintaining the data lake on BigQuery, including data ingestion, transformation, and scheduling. - Designing and implementing ETL pipelines in Python across banking, ERP, and CRM sources. - Experimenting with and deploying ML models for cash forecasting and business predictions. - Developing AI agents and MCP tool integrations while ensuring data quality, monitoring, and alerting across pipelines. Join Bachatt to be a part of a dynamic team working towards revolutionizing the savings and investment landscape for self-employed individuals in India!