Website:
neurodrift.ai
Job details:
NeuroDrift, a US-based AI voice and enterprise software company, is hiring two AWS Data Engineers with hands-on experience exposing data to LLMs through MCP servers or tool calling.
What you’ll do
- Build and maintain ingestion and ETL pipelines on S3, Glue (PySpark), Delta Lake, Redshift, Athena, and Airflow
- Onboard new sources (SFTP, SAP, Salesforce, REST APIs, file feeds) through a metadata-driven framework
- Build MCP servers and tools that let Claude and other LLM clients query governed financial data
- Implement access controls, masking, and audit logging on AI-facing data paths
- Contribute to the context layer: table and metric definitions, catalog metadata
- Support UAT and promote changes across non-prod, UAT, and prod
What we need (2.5+ years experience)
- 2.5+ years in data engineering on AWS in production
- S3, Glue (PySpark), Redshift, Athena, Airflow in work projects; Python and SQL
- Delta Lake or Iceberg on S3 (MERGE, OPTIMIZE, VACUUM)
- Dimensional modelling (facts, dimensions, SCD); validation and reconciliation built into pipelines
- Built an MCP server or LLM tool calling over data (MCP SDK, Claude, OpenAI tools, text-to-SQL)
Preferred
- Lambda, SNS, SQS, EventBridge in event-driven pipelines
- Metadata-driven ingestion; CI/CD across non-prod, UAT, prod
- Governed data access: IAM, Lake Formation, PII masking, Secrets Manager
- Finance or payments data; PCI-DSS, SOX, or SOC 2 exposure
How we work
- AI-assisted engineering from day one: Claude Code and Copilot are part of daily work
The setup
- Fully remote, India based
- 5:30 PM to 2:30 AM IST (US hours), five days a week
- Direct work with US stakeholders
- Notice period of 30 days or less
Click on Apply to know more.