The Role
Design and build AWS-based ingestion pipelines for structured and unstructured data supporting analytics and AI/GenAI use cases. Prepare AI-ready datasets through document parsing, chunking, and embedding workflows, while developing reusable, metadata-driven ingestion frameworks.
Summary Generated by Built In
Design ingestion pipelines feeding analytics and AI/GenAI use cases.
- Ingest structured and unstructured data from multiple sources into the AWS data lake
- Prepare AI-ready datasets, including document parsing, chunking and embedding pipelines
- Build reusable, metadata-driven ingestion frameworks
Requirements
- Must have: 4+ yrs, AWS (Glue, S3, Lambda, Step Functions, Kinesis), Python, PySpark.
- Nice to have: Bedrock, vector databases, OpenSearch
Skills Required
- 4+ years of experience
- Experience with AWS Glue
- Experience with Amazon S3
- Experience with AWS Lambda
- Experience with AWS Step Functions
- Experience with Amazon Kinesis
- Python
- PySpark
- Experience with Amazon Bedrock
- Experience with vector databases
- Experience with Amazon OpenSearch
Am I A Good Fit?
Get Personalized Job Insights.
Our AI-powered fit analysis compares your resume with a job listing so you know if your skills & experience align.
Success! Refresh the page to see how your skills align with this role.
The Company
What We Do
RADcube is a technology consulting and software development firm founded in 2015 and headquartered in Carmel, Indiana. It helps organizations turn enterprise ideas into practical innovations through digital transformation, custom software, data analytics, artificial intelligence, cloud computing, cybersecurity, and intelligent automation. The company serves healthcare, finance, government, and manufacturing clients, combining human-centric delivery with responsible, accountable technology solutions designed to produce measurable business outcomes.
.png){kind=logo}
