AI Data Engineer with AWS
Role: AI Data Engineer with AWS 100% Remote Duration : Long Term Responsibilities:
- Design and build scalable data pipelines for AI agents across cloud platforms
- Create and maintain agent‑ready data models, schemas, and data contracts
- Build and operate vector data pipelines (data prep, chunking, embeddings, indexing, re‑indexing)
- Integrate structured, semi‑structured, and unstructured data sources for agent consumption
- Develop MCP (Model Context Protocol) data adapters/connectors for databases, APIs, SaaS, files, and streams
- Define standard MCP request/response schemas and transformation logic
- Integrate MCPs with the MCP gateway (auth, routing, throttling, observability)
- Build CI/CD pipelines for MCP build, test, deployment, and rollback
- Implement CI/CD pipelines for data pipelines, datasets, and vector stores
- Automate environment promotion (dev/test/prod) for data assets
- Embed data quality checks (schema validation, freshness, completeness) into pipelines
- Design and operate real‑time streaming pipelines (event ingestion, enrichment, aggregation)Enable event‑driven data triggers for AI agents
- Build batch + streaming hybrid architectures for historical and real‑time context
- Develop and maintain certified data connectors for Low‑Code / No‑Code platforms
- Standardize enterprise data models for reuse by agents and citizen developers
- Manage secure data access using RBAC, managed identities, secrets, and tokenization
- Monitor data quality, drift, and freshness impacting agent behavior
- Implement data observability and lineage tracking across pipelines and MCPs
- Enforce data governance, classification, and compliance controls
- Optimize data performance, latency, and cost for agent workloads
- Experience developing these using AWS cloud services and opensource
Thanks & Regards, Sanju TekLeaders Inc 5151 Headquarters Dr. Suite 105 Plano TX 75024 Email: [email protected] www.tekleaders.com