Engineer 3, Agentic AI

Comcast Comcast · Media · Philadelphia, PA +1

This role focuses on designing, building, and operating agentic AI systems for Comcast's Xfinity applications, specifically enhancing the chat experience with AI-driven agents. The engineer will leverage tools like ADK and Gemini Enterprise to create reusable agents, integrate them into various workflows, and ensure production readiness with a focus on reliability, scalability, and observability. The role also involves applying AI across the software development lifecycle, including AI-augmented coding and testing, and contributing to AgentOps and AI governance.

What you'd actually do

  1. Design, build, and operate agentic systems that replace or augment human workflows
  2. Apply AI across the SDLC, including: Requirements and spec-driven development, System and agentic workflow design, AI-augmented coding and refactoring, AI-driven testing and defect remediation
  3. Build production-ready agent-based solutions with reliability, scalability, and observability
  4. Implement agent-to-agent, agent-to-UI, and human–AI orchestration
  5. Contribute to AgentOps, MLOps, and AI governance

Skills

Required

  • Agentic AI systems in production
  • Agent Development Kit (ADK)
  • Python
  • Gemini Enterprise
  • Spec-driven development
  • Prompt engineering
  • AI-assisted coding
  • AgentOps
  • LLM-as-a-Judge
  • Agent-to-agent, agent-to-UI, and human–AI collaboration patterns

Nice to have

  • Conversational AI platforms
  • production monitoring for agent-based systems

What the JD emphasized

  • 5-7 years building agentic AI systems in production
  • Hands-on experience with Agent Development Kit (ADK) and Python
  • Experience with Gemini Enterprise, or similar conversational AI platforms
  • Spec-driven development with AI integrated into the development lifecycle
  • Strong prompt engineering skills, including evaluation, iteration, and logging
  • Experience leveraging AI-assisted coding across multiple features or defects in parallel
  • Familiarity with AgentOps and production monitoring for agent-based systems
  • Experience with LLM-as-a-Judge or comparable evaluation techniques
  • Proven ability to design agent-to-agent, agent-to-UI, and human–AI collaboration patterns

Other signals

  • design, build, and operate agentic systems
  • AI-augmented coding and refactoring
  • AI-driven testing and defect remediation
  • production-ready agent-based solutions
  • agent-to-agent, agent-to-UI, and human–AI orchestration