**Active TS/SCI w/Polygraph REQUIRED** Please do not apply if you do not currently possess this level of clearance.
Telework: Up to 3 days/week
Job Description:
- The AI Engineer will work closely with system and software engineers to design, prototype, and integrate AI-enabled capabilities into the existing RAD architecture.
- This role centers on applying existing large language models (LLMs) to real mission workflows rather than training new models.
- The AI Engineer will build agentic solutions, systems of coordinated AI agents and prompts, that automate tasks currently performed manually, streamline authoring and reporting workflows, and enhance the overall effectiveness of intelligence operations.
Responsibilities:
- Agentic Solution Design & Development: Lead the design and development of AI-driven solutions from conception to deployment, building multi-agent workflows in which coordinated agents and prompts work together to produce outputs supporting reporting and dissemination. This includes prototyping, writing production-quality code, and maintaining deployed AI capabilities.
- LLM Integration: Integrate existing foundation models into the RAD architecture via APIs and orchestration frameworks, selecting the right model and approach for each task rather than building models from scratch.
- Prompt Engineering & Workflow Automation: Design, test, and refine prompts and agent instructions to reliably automate manual tasks, and decompose complex mission workflows into discrete steps an agent pipeline can execute.
- Evaluation & Reliability: Develop robust testing, evaluation, and validation strategies for AI-generated outputs, ensuring accuracy, consistency, and appropriate handling of edge cases before outputs reach analysts and reports.
- Collaboration & Communication: Serve as a key technical liaison, collaborating with cross-functional teams including system engineers, software developers, and domain experts. Effectively present and articulate recommended AI approaches, discussing the tradeoffs and implications of different implementations with both technical and non-technical stakeholders.
- Continuous Improvement: Stay current with the rapidly evolving LLM and agentic AI landscape (new models, orchestration frameworks, and tooling), continuously identifying practical opportunities to apply emerging capabilities to the system.
Required Experience:
-
- Strong Python development skills, with experience writing production-quality, maintainable code
- Hands-on experience building applications on top of existing LLMs (e.g., via APIs for commercial or self-hosted models)
- Experience designing multi-agent or multi-step AI workflows, including prompt chaining, tool use, and agent orchestration (e.g., LangChain, LlamaIndex, or custom frameworks)
- Strong prompt engineering skills and experience evaluating/validating LLM outputs
- Experience integrating AI capabilities into existing software architectures (RESTful APIs, microservices)
- Experience with the Amazon Web Services (AWS) cloud computing platform
Desired Experience:
-
- Experience with retrieval-augmented generation (RAG) pipelines and vector databases
- Familiarity with LLM observability and evaluation tooling
- Experience conducting exploratory data analysis on structured and unstructured datasets to prepare inputs for AI workflows
- Familiarity with MLOps/LLMOps practices for deploying and monitoring AI capabilities at scale
- Familiarity with domain knowledge surrounding government agency reporting and dissemination policies
----------
Excellent benefits package including 25 days PTO, 11 paid holidays, 100% employer-paid healthcare for employees and dependents - available day 1, 8% 401(k) employer match - immediate vesting.
Disclaimer: The salary range provided is an estimate based on current market conditions and may be adjusted based on factors such as experience, skills, and qualifications. The final salary offer will be determined after a thorough review of the candidate's background and alignment with the role. Please note that this range is subject to change and should be considered as a guideline rather than a definitive figure.
This is a full time position
