Platform and Reliability Engineer, Lead

Booz Allen Hamilton•McLean, VA

6h•$99,000 - $225,000•Hybrid

About The Position

Build and operate the secure, reliable foundation for enterprise agentic AI. Provide the cloud infrastructure, shared runtimes, model access, deployment pipelines, and observability services that enable engineering teams to deliver and operate AI solutions. Automate environments and security controls; monitor availability, latency, throughput, token consumption, and cost; and lead shared-platform incident response and recovery. Work with AI Engineering, Data Engineering, and Forward-Deployed Engineering to validate operational readiness and maintain deployment standards and runbooks. Accountability centers on shared platform reliability, security infrastructure, and production operations. U.S. citizenship is required due to the nature of work performed at the facility.

Requirements

Experience building and operating production infrastructure in AWS, Azure, or Google Cloud, including networking, identity, secrets management, and access controls.
Experience with infrastructure as code, containers, orchestration, and CI/CD pipelines, including automated security and deployment checks.
Experience applying site reliability engineering practices, including service objectives, alerting, incident response, capacity planning, and disaster recovery.
Experience implementing centralized logs, metrics, distributed traces, and dashboards to diagnose production failures and performance issues.
Knowledge of LLM operational requirements, including model gateways, rate limits, retries, timeouts, runtime isolation, and consumption costs.
Ability to automate operational workflows using a language such as Python or Bash, and troubleshoot distributed systems.
Ability to document support responsibilities, evaluate readiness evidence, and coordinate technical handoffs across teams.
Ability to obtain and maintain a Public Trust or Suitability/Fitness determination based on client requirements.
Bachelor's degree.
U.S. citizenship is required.

Nice To Haves

Experience with Kubernetes, Terraform, OpenTelemetry, LangSmith, Langfuse, or comparable tools.
Experience operating model gateways or AI workloads and implementing LLMOps practices.
Experience with FinOps, automated recovery, performance testing, or secure enterprise environments.

Responsibilities

Build and operate cloud infrastructure, shared runtimes, model access, deployment pipelines, and observability services for enterprise agentic AI.
Automate environments and security controls.
Monitor availability, latency, throughput, token consumption, and cost.
Lead shared-platform incident response and recovery.
Work with AI Engineering, Data Engineering, and Forward-Deployed Engineering to validate operational readiness.
Maintain deployment standards and runbooks.
Support shared-platform reliability, security infrastructure, and production operations.