AI/ML Platform & Agentic Automation Engineer

Peraton•Chantilly, VA

4d•$112,000 - $179,000

About The Position

Peraton is seeking an AI/ML Platform & Agentic Automation Engineer to design, develop, integrate, and maintain shared AI capabilities and intelligent workflow automation across enterprise platforms. The role focuses on integrating approved foundation models and managed AI services through reusable APIs, agentic workflows, and developer-facing tools, rather than developing foundation models from scratch. The engineer will collaborate with platform, DevSecOps, identity, cybersecurity, and operations teams to deliver reliable, auditable, and secure AI-enabled capabilities. The position includes integrating approved models and managed AI services into enterprise applications; developing reusable APIs and integration patterns; designing agentic workflows for platform engineering, service management, and operational processes; and building developer assistants and self-service automation. The engineer will also integrate AI services with enterprise identity, access-control, secrets-management, and audit mechanisms, while applying security boundaries, data-handling controls, and monitoring. The engineer will maintain platform components, workflows, prompts, integrations, and configurations through source control and engineering review processes; develop automated tests and evaluation scenarios; troubleshoot integrations and workflow failures; and coordinate controlled implementation of approved model and service updates. An active TS/SCI clearance with CI Polygraph is required. The stated target salary range is $112,000–$179,000.

Requirements

Active TS/SCI clearance with CI Polygraph.
BS/BA and 5 years of experience; an additional 4 years of experience may be considered in lieu of a degree.
Approximately 5–8 years of experience in software engineering, platform engineering, cloud engineering, workflow automation, applied AI/ML engineering, or a related technical discipline.
Hands-on experience integrating applications with foundation models or managed AI services through APIs.
Strong software development or scripting skills in Python or a comparable programming language.
Experience developing workflow automation that integrates with external tools, services, or APIs.
Experience with AWS services and cloud-native application development patterns.
Familiarity with Git-based development, CI/CD pipelines, containers, and modern software delivery practices.
Understanding of authentication, authorization, secrets management, and secure service integration.
Demonstrated troubleshooting skills across distributed applications and automated workflows.
Ability to collaborate effectively with software, platform, cybersecurity, and operations teams.

Nice To Haves

Hands-on experience with AWS Bedrock or comparable managed foundation-model services.
Familiarity with Bedrock Agents or other agent-orchestration frameworks.
Experience implementing retrieval-augmented generation (RAG) using approved enterprise data sources.
Experience integrating ServiceNow, GitLab, or comparable enterprise platforms through APIs.
Familiarity with Terraform, CloudFormation, Ansible, or other infrastructure automation tools.
Experience with OpenTelemetry or comparable application instrumentation and observability tools.
Familiarity with Kubernetes and container orchestration.
Experience working in classified, restricted, or otherwise highly regulated cloud environments.
Experience evaluating and testing large language model (LLM) applications, prompts, and agentic workflows.

Responsibilities

Integrate approved foundation models and managed AI services, including AWS Bedrock or comparable platforms, into enterprise applications and workflows.
Develop reusable APIs, service wrappers, and integration patterns for consistent access to model capabilities.
Implement configurable model-selection and integration approaches that allow model updates without extensive changes to consuming applications.
Support deployment and integration in cloud and restricted environments where approved AI services are available.
Design and implement agentic workflows to automate repeatable platform engineering, service management, and operational processes.
Integrate AI agents with approved tools and APIs, including IT service management platforms, source control systems, infrastructure automation, knowledge repositories, and observability services.
Establish workflow boundaries, approval requirements, tool permissions, auditability, and failure-handling mechanisms.
Develop reusable automation components for account provisioning, access requests, environment deployment, incident enrichment, technical documentation retrieval, and other approved use cases.
Develop and maintain AI-powered developer assistants, chat interfaces, and low-code/no-code capabilities.
Connect developer-facing tools to approved technical documentation, platform guidance, service catalogs, code examples, and engineering resources.
Integrate AI assistance into development workflows while protecting credentials, sensitive information, and privileged platform functions.
Collaborate with platform and developer-support teams to identify repetitive requests suitable for self-service tools and guided automation.
Integrate AI services with identity and access management, role- and attribute-based access controls, service identities, secrets management, and audit mechanisms.
Enforce security boundaries, access policies, and tenant-isolation requirements across AI services and agent workflows.
Coordinate with cybersecurity teams on guardrails, data-handling controls, logging, and authorization requirements.
Instrument AI services and automated workflows to monitor availability, usage, failures, latency, and performance.
Maintain AI platform components, workflow definitions, prompts, tool integrations, and configuration through source control and established engineering review processes.
Develop automated tests and evaluation scenarios to validate critical workflows before deployment to operational environments.
Troubleshoot model-service integrations, agent behavior, workflow failures, and developer-assistance capabilities.
Evaluate approved model and service updates and coordinate controlled implementation with AI/ML operations, assurance, and platform engineering teams.