Data Engineer- Manager

KPMG LLP; Washington (District of Columbia); On-site; USD 110,000 - 170,000; Full time

Job summary

KPMG LLP is seeking a Data Engineer to join our Audit Technology Alliance organization. You will design and implement data pipelines, transforming structured and unstructured client data into high-quality inputs for AI solutions.

You will collaborate with AI and solution architecture teams to define data schemas, support RAG pipelines, and ensure data quality across knowledge systems to drive effective AI workflows.

Qualifications

• Deep expertise in designing data pipelines for structured and unstructured data.
• Experience with AI-ready data preparation and RAG systems.
• Strong programming skills in Python and microservice architectures.

Responsibilities

• Take ownership of designing and implementing data pipelines for context engineering.
• Collaborate with AI and solution architecture teams to define data schemas.
• Support RAG pipelines and integration into AI agent workflows.
• Champion data quality with rigorous validation frameworks.

Skills

Python

Data pipelines

RAG data prep

Agile

Azure DevOps

Git

CI/CD

Databricks

Microsoft Fabric

Azure AI Search

Asynchronous messaging

Education

Bachelor’s degree

Master’s degree

Tools

Databricks

Microsoft Fabric

Azure AI Search

Azure DevOps

Git

CI/CD

Job description

KPMG is currently seeking a Data Engineer to join our Audit Technology Alliance organization.

Responsibilities:

• Take ownership of designing and implementing data pipelines focused on context engineering, transforming vast amounts ofstructured(e.g., transactional) and unstructured client data into high-quality inputs for our AI solutions
• Set the standard for data engineering excellence,establishingand evangelizing best practices for processing and modeling diverse data sets to be analyzed by advanced generative AI agents
• Serve as a key subject matter expert, collaborating closely with AI and solution architecture teams to define and deliver the specific data schemas and contextual payloads required by our AI orchestration frameworks
• Support the development ofRetrieval-Augmented Generation (RAG)and context engineering pipelines from audit knowledge sources and the integration into AI agent workflows; design and implement the use of metadata across knowledge systems to drive the use of context
• Champion data quality by developing and implementing rigorous validation frameworks to ensure the reliability of all data sources, which is critical for generating verifiable AI outputs
• Drive the product forward by personally prototyping and evolving our data engineering strategies, pioneering innovative techniques to handle complex data relationships andkeepour context engineering capabilities state-of-the-art
• Act with integrity, professionalism, and personal responsibility to uphold KPMG's respectful and courteous work environment

Qualifications:

• Minimum fiveyears of recent professional experience in data engineering, with a proventrack recordof building data solutions that support AI-driven or advanced analytics systems
• Bachelor’s degree from an accredited college or university;master’s degree from an accredited college or university in Computer Science, Engineering, Information Systems, or a related field is preferred
• Deepexpertisein designing and building data pipelines that process both structured and unstructured data, preparing it for advanced AI consumption using cloud platforms like Databricks and Microsoft Fabric
• Demonstrated experience in data preparation and structuring for Retrieval-Augmented Generation (RAG) systems, with hands-on knowledge of tools like Azure AI Search and a strong understanding of how data integrates into AI agent workflows
• Strong, independent programming skills in Python andsignificant experiencewith microservice architecture, including building data APIs and interacting with asynchronous messaging systems
• Proficiency with Agile methodologies and SDLC tools (Azure DevOps, Git, CI/CD) combined with excellent problem-solving skills to articulate complex data concepts and influence technical direction (200TEC)