The company is a secure software delivery firm serving federal and commercial customers, and this role sits with a government team and its technology partners on an emerging AI-powered engineering ecosystem.
You will embed with that team to design, connect, and run AI agents and agentic workflows inside a secure enterprise environment, combining large language models, agent frameworks, enterprise data, APIs, developer tooling, and platform services.
The work is hands-on and goes past research. The goal is to take AI prototypes and turn them into secure, repeatable agent capabilities that run in production.
You should understand both what current AI systems can and cannot do, and be able to turn new technology into working solutions quickly. You will test new models and frameworks, connect agents to enterprise systems, measure performance and reliability, and work alongside platform engineers and commercial partners.
The company works across Kubernetes, cloud environments, infrastructure as code, continuous delivery, GitOps, containers, CNCF and open source projects, and building cloud native applications.
Responsibilities
Design, build, and connect AI agents and multi-agent workflows using current LLM and agentic tools.
Build agent features that work with enterprise applications, APIs, data sources, developer tools, and mission systems.
Bring models, agents, tools, and enterprise data together into secure workflows that can run in controlled and classified environments.
Work with LLMs, RAG, embeddings, vector databases, tool and function calling, structured outputs, MCP, and related technologies.
Create ways for agents to find, access, reason over, and act on approved enterprise data and services safely.
Prototype and quickly test new models, agent frameworks, and AI capabilities to find where they add measurable mission or engineering value.
Build evaluation and testing frameworks that measure agent accuracy, reliability, safety, latency, cost, and task completion.
Put guardrails and policy controls in place for agent behavior, tool access, data access, and human approval points.
Connect agent capabilities to CI/CD and DevSecOps pipelines so development, testing, deployment, and lifecycle management are repeatable.
Work with platform engineers to run AI workloads on Kubernetes and OpenShift.
Work with commercial AI and technology partners to bring their capabilities into the wider engineering ecosystem.
Troubleshoot problems across models, agent frameworks, APIs, data sources, networking, identity, and infrastructure.
Build reusable patterns for agent deployment, configuration, observability, evaluation, and lifecycle management.
Spot recurring AI engineering problems that can be standardized, automated, or turned into reusable products.
Track fast-moving agentic AI technology and judge how well it fits secure government environments.
Requirements
Active Top Secret clearance.
2-5 years of hands-on experience building applications or systems with large language models and generative AI.
Experience designing and implementing AI agents or agentic workflows.
Strong programming skills in Python and/or another modern language.
Experience connecting AI systems with APIs, enterprise applications, databases, and external tools.
Experience with one or more agent frameworks or orchestration approaches.
Working knowledge of RAG, embeddings, vector databases, tool and function calling, structured outputs, and prompt engineering.
Experience building software in a Git-based, automated CI/CD environment.
Ability to prototype, test, troubleshoot, and iterate quickly in unclear conditions.
Solid grasp of software engineering basics, including testing, version control, APIs, debugging, and system design.
Ability to work well with platform engineers, government staff, and several technology vendors.
Preferred: experience with MCP and tool-based agent architectures.
Preferred: experience with multi-agent systems and agent orchestration.
Preferred: experience with OpenAI, Anthropic, Google, NVIDIA, or comparable foundation model ecosystems.
Preferred: experience with NVIDIA NIM, NeMo, or similar inference and model-serving technologies.
Preferred: experience with Red Hat OpenShift AI or Kubernetes-based AI platforms.
Preferred: experience with agent evaluation and observability frameworks.
Preferred: experience implementing AI guardrails, policy enforcement, human-in-the-loop workflows, or AI safety controls.
Preferred: experience with LangGraph, LangChain, LlamaIndex, Semantic Kernel, or comparable frameworks.
Preferred: experience with RAG pipelines, vector databases, knowledge graphs, and enterprise search.
Preferred: experience deploying AI systems in Secret or TS/SCI environments.
Preferred: experience with disconnected or air-gapped AI environments.
Preferred: experience integrating AI into developer or DevSecOps workflows.
Preferred: familiarity with GitLab, Jira, Confluence, Xacta, or similar engineering and compliance tools.
Preferred: experience with GPUs, model serving, inference optimization, or AI infrastructure.
Preferred: familiarity with UDS, Zarf, Pepr, Iron Bank, or similar secure software delivery technologies.
Preferred: experience moving AI prototypes into repeatable, production-ready capabilities.
Preferred: ability to assess new AI technologies quickly and make practical build, buy, or integrate decisions.
Conditions
Remote position within the United States.
Pay range is $148,750 - $201,250 USD, based on candidate experience and national benchmarking data that applies across all US locations.
The company is an equal-opportunity employer, and applicants who do not meet every listed requirement are still encouraged to apply.
Benefits
Medical, dental, and vision coverage, with premiums 100% paid by the company.
Health Savings Account, life insurance, and disability insurance.
401k retirement plan and company stock options.
Home office budget.
Flexible Time Off (FTO) for all full-time employees, plus all Federal Holidays, one week off for Thanksgiving, and two weeks off for Christmas and New Year's.
Paid parental leave.
Reimbursement for approved trainings and subscriptions.
Conference attendance covered, including travel, lodging, and fees.