Full Stack Engineer

Responsibilities

 

Peraton is seeking a talented and motivated Full Stack Engineer specializing in Agentic AI and External Integrations to join a dynamic team building and operating a cutting-edge Agentic AI platform.

 

In this role, you will be at the forefront of designing, developing, and maintaining the integrations and intelligent agent capabilities that power a next-generation decision-support platform — spanning delivery, infrastructure, runtime operations, and platform health. 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, 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, 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:

• 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
• Contribute to the build-out and operation of the Agentic AI platform across delivery, infrastructure, runtime operations, and platform health
• Collaborate across teams with a product mindset, keeping the end-user experience central to technical decisions
• Collaborates with stakeholders on workflows

Qualifications

 

Required Qualifications:

• Minimum of a BS degree with 5 years of experience, MS degree with 3 years, or PhD with meaningful exposure to AI/ML systems or LLM-based products
• 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
• Comfort operating with some ambiguity in a fast-moving environment

Clearance Requirements:

• US 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: