Sr. Platform Engineer - AI Agentic

Comcast • West Chester, PA

18h • Hybrid

About The Position

The AI Agentic Team will be responsible for designing, building, and operating intelligent agents end to end. They develop agent logic, workflows, integrations, and decision frameworks, then deploy those agents into production and own their ongoing behavior, reliability, and impact. The team monitors agent performance validates AI driven actions with human judgment, and iterates on designs as systems encounter real world complexity. By owning both construction and operations, they ensure agentic platforms are not just innovative, but reliable, secure, and scalable in production.

Requirements

• Cloud Infrastructure Engineering (AWS, Azure, or GCP)
• Infrastructure as Code (Terraform, Packer, Ansible, or equivalent)
• Python Programming for automation and operational tooling
• Monitoring, Logging, and Alerting Systems
• CI/CD Tools and Release Automation
• Security Fundamentals (IAM, secrets management, encryption, network security)
• 7-10 Years Relevant Work Experience

Nice To Haves

• Experience supporting AI, ML, or Agentic platforms in production
• Familiarity with data and streaming platforms (e.g., S3, SQS, Kafka‑like systems)
• Understanding of networking and protocol standards
• Exposure to hardware security modules (HSMs) or advanced key management solutions
• Experience operating large‑scale distributed systems
• Cloud cost optimization and performance tuning experience

Responsibilities

• Design, implement, and operate cloud infrastructure supporting scalable, highly available AI‑enabled and Agentic platforms.
• Apply Infrastructure as Code (IaC) practices (e.g., Terraform, Packer, Ansible) to provision and manage cloud resources consistently and securely.
• Monitor platform health using metrics, logs, dashboards, and alerts, applying critical thinking to distinguish infrastructure, application, and AI‑driven failures.
• Lead troubleshooting and resolution of complex cloud and platform issues, including distributed system and integration failures.
• Develop and maintain automation and tooling (primarily Python and shell scripting) to improve reliability, diagnostics, and operational efficiency.
• Implement and evolve observability solutions (e.g., Prometheus, Splunk, Grafana, CloudWatch) to improve system transparency and alert quality.
• Collaborate with application, data, and AI teams to ensure platforms are operable, observable, and scalable prior to and after release.
• Support CI/CD pipelines and release workflows, enabling safe and repeatable deployments across environments.
• Ensure secure cloud operations, including secrets management, access controls, encryption, and secure networking practices.
• Apply foundational AI literacy to understand agent lifecycles, orchestration patterns, and non‑deterministic execution behaviors that impact operations.
• Use AI‑assisted tools to enhance investigation, documentation, and optimization, while validating outputs with sound engineering judgment.
• Contribute to and maintain runbooks, platform documentation, and operational standards.
• Participate in on‑call rotations and act as an escalation point during production incidents.
• Perform other duties and responsibilities as assigned.

Benefits

• Benefits should connect you to the support you need when it matters most, and should help you care for those who matter most. That's why we provide an array of options, expert guidance and always-on tools that are personalized to meet the needs of your reality—to help support you physically, financially and emotionally through the big milestones and in your everyday life. Please visit the benefits summary on our careers site for more details.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Number of Employees: 5,001-10,000 employees