Build Applied AI for Secure Mission Software
Help turn generative-AI concepts into dependable capabilities used within secure planning and decision-support software.
At Rackner, you will integrate large language models, retrieval-augmented generation, agentic AI, and inference workflows into an established software application supporting a high-impact national-security mission. You will work across AI, software engineering, cybersecurity, DevSecOps, and customer technical teams to move capabilities beyond standalone demonstrations and into practical product workflows.
This role offers the opportunity to deepen your applied-AI experience, influence how emerging capabilities are designed and evaluated, and contribute to software where reliability, security, and mission usefulness matter.
What You’ll Do
- Build and integrate LLM-enabled capabilities into secure application workflows.
- Develop or integrate retrieval-augmented generation and agentic-AI components.
- Design prompts, system instructions, and inference workflows that support real user and mission needs.
- Connect AI capabilities with existing backend services and decision-support processes.
- Evaluate outputs for grounding, reliability, accuracy, and usefulness.
- Develop tests for AI-enabled functionality and support broader integration testing.
- Demonstrate working prototypes and incorporate technical and user feedback.
- Document AI designs, workflows, limitations, and implementation decisions.
- Participate in code reviews, technical reviews, and security-remediation activities.
- Collaborate with software engineers, security professionals, DevSecOps teams, and customer stakeholders.
What You Bring
- Four or more years working across AI/ML, large language models, retrieval-augmented generation, and prompt engineering.
- A master’s degree or Ph.D. in AI/ML or a related field.
- Hands-on delivery of LLM-enabled software and RAG capabilities.
- Practical knowledge of agentic AI, multi-step workflows, or similar orchestration approaches.
- Familiarity with building or supporting inference pipelines.
- The ability to explain your technical contributions, design decisions, and results.
- Strong collaboration and technical-documentation skills.
Preferred Background
- A track record of moving AI capabilities beyond coursework, personal projects, or demonstrations into operational software.
- Practical knowledge of evaluating AI outputs and addressing weak grounding, hallucinations, or unreliable responses.
- Familiarity with secure software-development and DevSecOps practices.
- Exposure to classified, restricted, disconnected, or controlled development environments.
- Collaboration with backend, cybersecurity, and platform-engineering teams.
- Work supporting defense, government, aerospace, or other regulated environments.
- Familiarity with containerized OpenShift or Kubernetes environments.