AI Engineer (Data Pipelines & RAG)

Job Role- AI Engineer (Data Pipelines & RAG)

Job Type- Full-time

Work Mode- Remote(6 days working)

We are looking for a hands-on AI/Data Engineer (4–7 years) to build and scale data pipelines powering GenAI and agentic applications. You’ll architect data models, build ETL/ELT workflows, and integrate pipelines with RAG-based systems in a fast-paced startup environment.

What You’ll Do

Data Pipelines & Modeling

- Build scalable ETL/ELT pipelines (batch & streaming) using Python + Spark - Automate ingestion from databases, APIs, files, SharePoint and other document sources - Process & structure unstructured files (PDFs, tables, charts, drawings, etc.) - Own chunking, indexing & embedding strategies for RAG/LLM use cases - Design logical & physical data models, schema mappings & data dictionaries

GenAI & RAG Integration

- Feed real-time data into LLM prompts - Build retrieval workflows for downstream agent/RAG systems in RE/Construction

Observability & Governance

- Implement monitoring, alerting & logging for pipeline reliability - Apply IAM, Unity Catalog and other data privacy/security controls

CI/CD & Automation

- Use DevOps workflows with GitHub Actions/Azure DevOps/CircleCI - Build reproducible infra using Terraform / ARM templates - Use Prefect / Airflow for orchestration

What You’ll Need

- 5+ years in data engineering, with 1–2 years working on pipelines for unstructured data & RAG systems - Strong Python + SQL, experience with dlt, DuckDB, DVC - Azure cloud experience in production - Experience with chunking/indexing strategies for RAG - Strong Git/CI/CD workflows - Familiarity with Prefect or equivalent - Good to Have: MLflow, Docker/K8s, Computer Vision, agentic AI concepts, governance & privacy frameworks (GDPR)