Principal Agentic AI Platform Engineer

Location:

Virtual, US

Avaya is an enterprise software leader that helps the world’s largest organizations and government agencies forge unbreakable connections.

The Avaya Infinity™ platform unifies fragmented customer experiences, connecting the channels, insights, technologies, and workflows that together create enduring customer and employee relationships.

We believe success is built through strong connections – with each other, with our work, and with our mission. At Avaya, you'll find a community that values your contributions and supports your growth every step of the way.

Learn more at

We are seeking a hands-on, forward-thinking Principal Platform Engineer to pioneer the integration of Agentic AI into our core engineering ecosystem. In this role, you will design, build, and scale reusable agentic systems that fundamentally transform both platform development and day-two operations.

Rather than treating AI agents merely as production-operation assistants, you will embed these intelligent capabilities into the very fabric of our engineering lifecycle. By extending established cloud-native practices with secure agent tooling and rigorous evaluation frameworks, you will establish a scalable blueprint for autonomous operations across the entire organization. This position demands a rare combination of startup-like urgency, hands-on technical ownership, and an unyielding commitment to security, compliance, and systems reliability.

• Create a coherent agentic platform engineering approach: shared tool interfaces, reusable skills/workflows, coding conventions, evaluation harnesses, telemetry and adoption patterns.
• Develop agents and tools integrated with Terraform, Kubernetes, Argo CD/Git Ops, cloud APIs, CI/CD, API gateways, Kafka, Redis, relational/document databases, observability and change-management systems.
• Accelerate platform development with AI-supported module/chart creation, code review, infrastructure plan interpretation, test generation, dependency analysis and safe pull-request workflows.
• Engineer day-two agents for health and drift detection, incident triage, correlated diagnostics, root-cause hypotheses, capacity analysis, upgrade readiness, runbook assistance and recovery verification.
• Build agentic development workflows for Kafka, Redis, relational/document database deployment and scaling, schema/configuration checks, upgrade planning, performance diagnosis, capacity assessments and secure API gateway changes.
• Use Prometheus, Grafana, Loki, Thanos, Grafana Alloy and Open Telemetry as operational signal sources; engineer safe telemetry retrieval, correlation, retention-aware queries and verifiable diagnostic recommendations.
• Build controlled operational workflows progressing from read-only diagnosis to recommended actions, gated changes and policy-authorized execution where justified.
• Enforce scoped identity, least privilege, environment isolation, secrets protection, prompt/tool-injection resistance, input/output validation, human approvals, audit trails, timeouts, budgets, kill switches and rollback boundaries.
• Implement evaluation of agent correctness, false positives, tool behavior, failure handling, security conformance and outcome quality before production rollout.
• Embed compliance requirements into agent workflows: explainable decisions, traceable evidence, approved change paths, data minimization and continuous control validation for FedRAMP/PCI DSS/SOC 2 environments.
• Partner with security, SRE/Cloud Ops and platform teams to define where agents may observe, recommend or act; document accountable owners and escalation paths.
• Coach engineers through pairing, playbooks, examples and metrics so…