Software Engineer - Agentic AI

Comcast
PA - Philadelphia, 1800 Arch St2026-04-22Full time

About the job

We are evolving our chat experience from human-assisted to fully agentic. As an AI Agentic Software Engineer, you will help rewrite an existing production application into an end-to-end agentic platform, with a strong passion for customer experience and a commitment to building intuitive, high-quality interactions.

Responsibilities

Design, build, and operate agentic systems that replace or augment human workflows

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

Treat AI as a collaborating system, not a one-off tool

Evaluate and iterate on AI outputs (e.g., LLM-as-a-Judge)

Build production-ready agent-based solutions with reliability, scalability, and observability

Implement agent-to-agent, agent-to-UI, and human–AI orchestration

Contribute to AgentOps, MLOps, and AI governance

Ensure ethical, compliant, and responsible AI use.

Clearly communicate how AI is used in your engineering workflows

Share patterns and best practices with the team

Partner with product, UX, and platform teams to deliver cohesive experiences.

Qualifications

Minimum

2+ years building agentic AI systems in production, or equivalent experience designing, shipping, and operating scalable, production-grade software (APIs, platforms, workflow engines, or customer-facing applications)

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

Preferred

No preferred qualifications listed.