Senior Data Engineer - GenAI & AWS (Remote/Hybrid)

BlackCube Labs; United States; Hybrid; USD 180,000 - 240,000; Full time

Job summary

BlackCube Labs is seeking a Senior Data Engineer (GenAI & AWS) to design and implement data pipelines across AWS services, focusing on Retrieval-Augmented Generation and AI agent integrations. The role requires extensive experience with vector databases, embeddings, and building scalable data architectures.

The candidate will work in a remote/hybrid setup with travel to client sites for workshops and meetings, prioritizing timezone coverage across the West Coast and beyond.

Qualifications

• 12+ years of experience in data engineering or data platform roles.
• Strong AWS and Python expertise with a focus on GenAI workflows.
• Experience designing data pipelines, ETL/ELT, and automation.
• Proficiency with vector databases, embeddings, and RAG patterns.
• Hands-on experience deploying AI agents and large language models.
• Familiarity with CI/CD pipelines and IaC tooling.
• Excellent collaboration and communication across time zones.

Responsibilities

• Design and develop data pipelines using AWS Step Functions, Lambda, S3, Textract, and Comprehend.

Skills

Python

SQL

Time zone coverage

Cloud computing

Communication

Python proficiency

Python scripting

Team collaboration

Tools

AWS Step Functions

AWS Lambda

AWS S3

Amazon Textract

Amazon Comprehend

Vector databases

Embeddings

RAG

Amazon Bedrock

Claude Agent SDK

AgentCore Runtime

GitHub Actions

CI/CD

AWS IAM

API integrations

TypeScript

AWS Glue

OpenSearch

Pinecone

pgvector

LangChain

LlamaIndex

Terraform

AWS CDK

Document AI / OCR

Claude Agent SDK

Job description

BlackCube Labs is seeking a Senior Data Engineer (GenAI & AWS) to design and implement data pipelines across AWS services, focusing on Retrieval-Augmented Generation and AI agent integrations. The role requires extensive experience with vector databases, embeddings, and building scalable data architectures.

The candidate will work in a remote/hybrid setup with travel to client sites for workshops and meetings, prioritizing timezone coverage across the West Coast and beyond.