Required Qualifications
- Minimum of a BA/BS degree with 2 years of experience; MS degree with 0 years of experience
- Bachelor's degree in Computer Science, Software Engineering, Cybersecurity, Information Systems, or Computer Engineering
- Hands-on experience building with AI agents — multi-step reasoning, tool use, RAG pipelines, or autonomous task execution
- Strong Python skills (3.12+); comfort with async/await patterns, type hints, and modern Python tooling
- Familiarity with agentic frameworks and an understanding of the underlying concepts (chains, tool calling, agent loops) that transfer across tools
- Experience operating CI/CD pipelines in GitHub Actions and/or GitLab CI
- Experience with cloud infrastructure (AWS) including VPC, IAM, S3, RDS, CloudTrail, and KMS
- Hands-on experience with Kubernetes (Amazon EKS preferred), including cluster upgrades, RBAC, Helm, and GitOps workflows
- Experience building and maintaining Terraform/OpenTofu infrastructure-as-code
- Strong skills in release planning, deployment automation, validation, and rollback procedures
- Experience with monitoring, logging, and alerting systems (CloudWatch, Prometheus, Grafana, or similar)
- Ability to perform anomaly detection, log analysis, and troubleshoot configuration and security issues
- Practical understanding of secrets management, least privilege, supply chain security, and audit evidence
- Experience performing vulnerability remediation and managing IAVM or similar compliance requirements
- Familiarity with DAST and runtime security testing tools (e.g., OWASP ZAP, Burp, Nuclei)
- Experience with identity provider integration (SSO/SAML/OIDC) and RBAC administration
- Comfort operating with some ambiguity in a fast-moving environment
Clearance Requirements
- U.S. Citizenship is required
- Ability to obtain a Public Trust
Desired Qualifications
- Production experience with agent frameworks (LangChain, LangGraph, LlamaIndex, CrewAI, AutoGen, OpenAI Agents SDK, Anthropic tool-use, or comparable) and a sound point of view on when each is the right tool
- Experience designing and operating retrieval-augmented generation (RAG) systems — chunking strategies, embedding models, vector stores, hybrid retrieval, reranking, and grounding/citation patterns
- Experience integrating with knowledge graphs, document stores, or curated content repositories as agent-accessible sources
- Experience evaluating agent and LLM systems — building eval harnesses, golden datasets, regression testing, and observability for non-deterministic systems
- Exposure to orchestration patterns: supervisor agents, parallel tool calls, human-in-the-loop flows, DAG-based pipeline execution
- Experience building plugin or extension systems: dynamic code loading, container isolation, API mixin patterns
- Familiarity with prompt engineering, evaluation frameworks, or agent observability
- Familiarity with federal compliance environments: FedRAMP, FIPS 140-2/3, IronBank container hardening, OPA policy enforcement, or Section 508 accessibility
- Experience with observability tooling: OpenTelemetry, Jaeger, Prometheus, Grafana, or similar distributed tracing/metrics stacks
- Experience with container orchestration (Docker SDK, Kubernetes) and distributed storage (S3, MinIO, JuiceFS)
- Experience designing synthetic or transactional monitoring tied to user journeys and critical service flows
- Experience developing SLOs, service health indicators, and high-fidelity operational alerting
- Experience with modern delivery patterns such as trunk-based development, merge-request-driven change, and automated release quality controls
- Experience in security-focused CI/CD or DevSecOps environments
- Experience coordinating with customer security teams or operating within compliance frameworks
- Prior work building internal tooling, enterprise automation products, or platforms for government customers
Peraton is seeking a talented and motivatedFull Stack & DevSecOps Engineerto join a dynamic team building and operating a cutting-edge Agentic AI platform. This hybrid role sits at the intersection of application engineering and platform operations — combining the responsibilities of a Full Stack Engineer specializing in Agentic AI and External Integrations with those of a DevSecOps / Platform Engineer.
In this role, you will design, develop, and maintain the integrations and intelligent agent capabilities that power a next-generation decision-support platform, while also owning the delivery infrastructure, CI/CD pipelines, cloud operations, and platform health that keep it running securely and reliably. You will work across the full stack to connect AI agents with diverse external data sources, package real-world capabilities as reliable agent tools, and ensure that the systems you build are secure, scalable, observable, and production ready.
If you are passionate about applied AI, thrive in fast-moving environments, and take pride in building platforms that real users depend on — from the application layer down to the infrastructure — this is an opportunity to make a meaningful impact supporting critical missions.
Location:Columbus, Ohio — candidates must currently reside in the area or be willing to relocate.
Key Responsibilities
Full Stack & Agentic AI Engineering
- Design and build integrations to external sources of information, including public APIs, licensed data feeds, partner systems, customer enterprise systems, web content, document repositories, and structured databases
- Package external capabilities as agent tools and skills with clean interfaces, predictable inputs/outputs, sound error handling, and documentation usable by both AI agents and human configurators
- Develop and maintain full-stack components spanning FastAPI/Python backends, React frontends, Docker containerization, and PostgreSQL
- Build and consume web APIs (REST, GraphQL, or comparable), handling production integration concerns such as authentication, pagination, rate limiting, retry/backoff, schema mapping, deduplication, and caching
- Implement and maintain workflow and task orchestration pipelines using systems such as Airflow, Prefect, Celery, or comparable agent orchestration patterns
- Integrate LLMs into production or near-production applications, leveraging APIs such as OpenAI, Anthropic, or AWS Bedrock
- Apply security best practices specific to agentic and external integration work — including secrets management, OAuth and API-key handling, defensive parsing, and prompt-injection awareness
- Collaborate across teams with a product mindset, keeping the end-user experience central to technical decisions
DevSecOps & Platform Engineering
- Build and maintain CI/CD pipelines across GitHub Actions and/or GitLab CI, enabling secure, repeatable, and efficient delivery workflows
- Implement and improve automated testing and quality gates within the software delivery lifecycle, including build validation, integration checks, security testing, and deployment controls
- Plan and execute releases and deployments — coordinating change windows, managing release artifacts, running deployment automation, validating post-deployment health, and supporting rollback procedures
- Support operational ownership of Amazon EKS / Kubernetes environments, including cluster lifecycle activities, upgrades, troubleshooting, RBAC, Helm-based deployments, pod identity, and GitOps-aligned workflows
- Build and maintain AWS infrastructure supporting platform and application needs across services such as VPC, IAM, S3, RDS, CloudTrail, and KMS
- Contribute to infrastructure provisioning and lifecycle management through OpenTofu / Terraform and related infrastructure-as-code practices
- Administer user management for the platform — identity provider integration (SSO/SAML/OIDC), RBAC, provisioning and deprovisioning workflows, and periodic access reviews
- Design and operate a mature monitoring, logging, and alerting stack using CloudWatch, Prometheus/Grafana, or equivalent tooling
- Routinely assess system logs to detect anomalies, configuration drift, misuse, and security-relevant events; triage findings and drive remediation
- Build and maintain synthetic and transactional monitoring that exercises real authentication flows, user journeys, and critical service transactions
- Track and remediate Information Assurance Vulnerability Management (IAVM) notices and other vulnerability advisories — maintain inventory accuracy, drive patching to closure, and produce compliance reporting evidence
- Implement and maintain DAST and runtime security testing in delivery pipelines using tools such as OWASP ZAP, Burp, Nuclei, or equivalent
- Support security-focused CI/CD practices including secrets management, least privilege, software supply chain integrity, and audit evidence generation