AI Engineer in Content Quality

AI Engineer – Content Quality

As an AI Engineer for Content Quality, you will collaborate with engineers to build, execute, and iterate on agent orchestrations, automated workflows, and system integrations that power content quality processes. This role focuses heavily on Model Context Protocol (MCP) integrations, agent skills, AI orchestration, and Google’s internal infrastructure. This position is ideal for a highly motivated builder who is eager to learn, comfortable working from technical specifications, and deeply committed to the quality and reliability of what they ship. 

You’ll gain hands-on experience building systems that use cutting-edge AI technologies to automate complex workflows.

Responsibilities:

Agent Orchestration & Automated Workflows

Build and improve AI agent orchestrations that automate content quality workflows and reduce the need for manual intervention.

Develop automated workflows that leverage LLMs, tools, and agent chaining.

Collaborate with engineers and domain specialists to design and refine workflow logic.

Create and maintain clear workflow documentation so domain specialists can understand, tune, and improve processes.Iterate on workflows based on performance, quality, and operational feedback.

Integration & MCP Development

Develop integrations between AI models and external platforms using Model Context Protocol (MCP) servers and similar frameworks.

Build primarily in Python, with an emphasis on reliable and maintainable integrations.

Work with APIs, HTTP, REST, and client-server architectures.

Implement robust error handling, retries, and failure recovery to ensure reliable integrations.

Maintain and update integrations as underlying systems, APIs, and tools evolve.

Develop and maintain agent skills and tool integrations.

Google Infrastructure & Tooling

Work with Google’s internal ecosystem and infrastructure, including:

PLX for data and infrastructure workflows.

Buganizer for issue tracking and project management.

Jet Ski for analytics and data workflows.

Use CLI-based development tools, including the Gemini CLI, to improve development, debugging, and testing efficiency.

Implement monitoring and audit logging to ensure agent actions are traceable, observable, and queryable.

Help build reliable systems that can be monitored and maintained at scale.

Requirements:

Technical Skills:

Proficiency in Python.

Basic understanding of SQL and the ability to write simple queries.

Familiarity with:

API integrations

HTTP and RESTful APIs

Client-server networking

LLM APIs 

Prompt engineering

Structured outputs

Tool use and agent chaining

Understanding of AI/ML frameworks and emerging protocols such as Model Context Protocol (MCP).

Ability to understand technical specifications and translate them into reliable implementations.

Google Ecosystem & Development Tools

Experience with, or a strong willingness to learn, Google internal tools such as: PLX, Buganizer, Jet Ski

Comfortable working with CLI-based development tools, including the Gemini CLI.

Willingness to learn new internal infrastructure and development environments quickly.

Professional Skills:

Comfortable working from a provided technical specification and implementing solutions accurately with guidance from senior engineers.

Strong attention to detail and commitment to code and workflow quality.

Ability to balance speed, quality, and reliability in a fast-changing environment.

Strong communication and collaboration skills.

Clear, structured thinking and strong problem-solving abilities.

Self-motivated and eager to learn and grow in the field of AI engineering.

Comfortable working in a collaborative environment and incorporating feedback from engineers and domain specialists.