Data Engineer

Themesoft Inc; Chandler (IN); Hybrid; USD 82,656 - 137,760; Part time

Job summary

Themesoft Inc is seeking a data engineer to implement AI-enabled data capabilities on Google Cloud, focusing on ingestion, transformation and distribution for big data apps. You will leverage LangChain, LangGraph/ADK and agentic frameworks to automate data governance, quality and compliance.

Collaborate with principal engineers, product managers and data engineers in a matrix org to roadmap, deliver key data capabilities based on priority. Hybrid work model in Chandler/Charlotte area.

Qualifications

• Must have 5+ years of data engineering experience with cloud data solutions and Spark-based ingestion/processing.
• Must have 3+ years of Data Lakehouse architecture and design with Python, pySpark, Kafka, Airflow, Google Cloud Storage, BigQuery, Data Proc, Cloud Composer.
• Hands-on experience with Kafka, Flink, and Spark streaming.

Responsibilities

• Implement and operationalize modern AI-enabled data capabilities on Google Cloud to ingest, transform, and distribute data for a variety of big data apps
• Leverage AI/Agentic frameworks to automate data management, governance, and data consumption capabilities - data pipelines, data quality, metadata, data compliance, etc.
• Work within a matrix org. with principal engineers, product managers, and data engineers to roadmap, plan, and deliver key data capabilities based on priority

Skills

LangChain

LangGraph/ADK

Agentic frameworks

RAG

GraphRAG

MCP

GCP experience

Tools

Python

pySpark

Spark

Kafka

Airflow

BigQuery

Data Proc

Cloud Composer

Google Cloud Storage

Job description

Job Description:

• Implement and operationalize modern AI-enabled data capabilities on Google Cloud to ingest, transform, and distribute data for a variety of big data apps
• Leverage AI/Agentic frameworks to automate data management, governance, and data consumption capabilities - data pipelines, data quality, metadata, data compliance, etc.
• Demonstrable skills (recent) using AI tools such as LangChain, LangGraph/ADK, agentic frameworks, RAG, GraphRAG, and using MCP to build agent-based data capabilities
• 5 plus years of experience in data engineering including hands-on experience working with Cloud data solutions: creating/supporting Spark based ingestion and processing
• 3 plus years of experience with Data lakehouse architecture and design, including hands-on experience with Python, pySpark, Kafka, Airflow, Google Cloud Storage, BigQuery, Data Proc, Cloud Composer
• Hands-on experience developing data flows using Kafka, Flink, and Spark streaming

Must Have:

• GCP - 5 to 6 years.
• AI exposure - 6 months to a year
• Demonstrable skills (recent) using AI tools such as LangChain, LangGraph/ADK, agentic frameworks, RAG, GraphRAG, and using MCP to build agent-based data capabilities
• 5 plus years of experience in data engineering including hands-on experience working with Cloud data solutions: creating/supporting Spark based ingestion and processing
• 3 plus years of experience with Data Lakehouse architecture and design, including hands-on experience with Python, pySpark, Kafka, Airflow, Google Cloud Storage, Big Query, Data Proc, Cloud Composer
• Hands-on experience developing data flows using Kafka, Flink, and Spark streaming

In this role candidates will:

• Implement and operationalize modern AI-enabled data capabilities on Google Cloud to ingest, transform, and distribute data for a variety of big data apps
• Leverage AI/Agentic frameworks to automate data management, governance, and data consumption capabilities - data pipelines, data quality, metadata, data compliance, etc.
• Work within a matrix org. with principal engineers, product managers, and data engineers to roadmap, plan, and deliver key data capabilities based on priority

LOCATION - (Preferred) CHANDLER, CHARLOTTE, MINNESOTA, LAS COLINAS

Contract

Hybrid

229597-1

12+ Months

Thank you for taking the time to read this email.