> Markdown version of [/jobs/ext/3557435-senior-full-stack-engineer-agentic-external-integrations](https://www.wearedevelopers.com/jobs/ext/3557435-senior-full-stack-engineer-agentic-external-integrations). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Senior Full Stack Engineer - Agentic & External Integrations - **Company:** Peraton Inc - **Location:** Reston, VA, United States - **Experience:** Expert - **Salary:** $146,000.0 - $234,000.0 - **Contract:** Permanent contract - **Skills:** LangGraph Framework, Application Programming Interfaces (APIs), Artificial Intelligence, Airflow, Amazon Web Services, Amazon S3, User Authentication, Databases, Data Deduplication, Distributed Data Store, Federal Information Processing Standards (FIPS), Graph Database, Information Retrieval, Python (Programming Language), Key Management, PostgreSQL, Machine Learning, OAuth, Regression Testing, OpenAI, Prometheus, Systems Integration, Datadog, LangChain, ReactJS, Retrieval-Augmented Generation, Large Language Models, Grafana, Prompt Engineering, Llamaindex, Caching, Web Content, Agentic-AI, Rate Limiting, Fastapi, Build Management, Containerization, Kubernetes, CrewAI, AutoGen, Graphql, Machine Learning Operations, Celery, Front End Software Development, Observability for Autonomous Agents, Pagination, Dynatrace, Human in the Loop, Docker, Web Api - **Published:** October 2, 2026 - **Apply:** https://diversityjobs.com/main/sendform/8/8/28176/1/18497418?backUrl=%2Fcareer%2F18497418%2FSenior-Full-Stack-Engineer-Agentic-External-Integrations-Virginia-Reston ## About the Role * BS degree with 8 years professional experience, Associates degree with 10 years professional experience or MS degree with 6 years professional experience, or high school diploma/equivalent and ten years professional experience 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 - and integrating LLMs into production or near-production applications * Demonstrated experience designing and building integrations to external sources of information - public APIs, licensed data feeds, partner systems, customer enterprise systems, web content, document repositories, or structured databases * Demonstrated experience packaging external capabilities as agent tools or skills with clean interfaces, predictable inputs and outputs, sound error handling, and documentation that AI agents and the humans configuring them can rely on * Strong Python skills (3.12+); comfort with async/await patterns, type hints, and modern Python tooling * Comfort working across the stack: FastAPI/Python backends, React frontends, Docker containerization, and PostgreSQL * Experience building and consuming web APIs (REST, GraphQL, or comparable) and handling the integration concerns that make external data trustworthy in production - authentication, pagination, rate limiting, retry/backoff, schema mapping, deduplication, and caching * Experience with workflow or task orchestration systems (Airflow, Prefect, Celery, or similar distributed execution frameworks) or comparable agent orchestration patterns * Familiarity with agentic frameworks and an understanding of the underlying concepts (chains, tool calling, agent loops) that transfer across tools * Experience working with LLM APIs (OpenAI, Anthropic, AWS Bedrock, or similar) * Solid grounding in the security concerns specific to agentic and external integration work - secrets management, OAuth and API-key handling, rate-limit etiquette, defensive parsing, and prompt-injection awareness * A product mindset: you think about the end user, not just the technical implementation * Comfort operating with some ambiguity in a fast-moving environment * US Citizenship is a requirement for this position Nice-to-Haves * 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 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) * Prior work building internal tooling, enterprise automation products, or platforms for government customers ## Description Wire agents to the real world. Every integration you ship expands what our agentic platform can do - new data sources, new tools, new autonomous workflows for analysts and operators. * Work on the leading edge of technology. Python 3.12+, FastAPI, React, Postgres, Docker, and the latest AI models across OpenAI, Anthropic, Google, and more. * Build next-generation agentic tools is the norm. Agentic flows, human-in-the-loop, evals - you'll be practicing this daily with our customers. * Product-centric mindset. FedRAMP, FIPS, IronBank, OPA are in scope, and we ship like a product org. What You'll Do * Design and build integrations between our agents and external sources - public APIs, licensed feeds, partner systems, customer enterprise systems, document repositories, and structured databases. * Package those integrations as agent-callable tools: clean interfaces, predictable I/O, sound error handling, and documentation the agents (and the humans configuring them) can actually rely on. * Own the production concerns that make external data trustworthy - auth, pagination, rate limiting, retry/backoff, schema mapping, deduplication, caching. * Build and evolve orchestration for multi-step agent workflows, including tool routing, parallel execution, and human-in-the-loop checkpoints. * Contribute across the stack - FastAPI services, React UI for tool configuration and observability, Postgres schemas, containerized deploys. * Instrument what you ship. Traces, metrics, evals, and regression tests for non-deterministic agent behavior. * Partner with platform, security, and mission engineers to move capabilities from prototype to production inside federal compliance boundaries.