AI Engineer – LLM & Agentic Workflows
About The Position
The AI Engineer will apply existing large language models to real mission workflows, building agentic solutions that automate manual work and streamline reporting. The role supports an enterprise reporting and dissemination system integrating AI-enabled capabilities into mission workflows. Work is hybrid in Annapolis Junction, Maryland, with required in-person work and up to three days per week of telework; applicants must live within commuting distance. An active TS/SCI clearance with polygraph is required, and the employer does not sponsor new clearances or upgrades. The position involves designing and deploying multi-agent AI workflows, integrating foundation models through APIs and orchestration frameworks, refining prompts and agent instructions, and developing strategies to test and evaluate AI outputs. The engineer collaborates with engineers and domain experts and presents tradeoffs. Approximate compensation is $77.31–$85.36 per hour. The listed range excludes the employer’s 401(k) contribution and varies by qualifications, experience, and selected compensation model. Three models are available: Max Rate, With Bonus, and With Bonus and PTO. The lower end reflects a no-bonus option with five weeks of PTO; the upper end reflects the Max Rate option without bonus or PTO. PTO and bonuses depend on the selected model and role eligibility.
Requirements
- At least 3 years of relevant experience.
- Bachelor’s degree in a STEM discipline.
- Strong production-quality Python skills.
- Experience building applications on existing LLMs via APIs.
- Experience with multi-agent workflows, prompt chaining, and tool use, using LangChain, LlamaIndex, or custom approaches.
- Prompt engineering and LLM output evaluation skills.
- Experience integrating AI into RESTful APIs and microservices.
- AWS experience.
- Currently hold an active TS/SCI clearance with polygraph; clearance sponsorship or upgrades are not available.
- Live within commuting distance of the listed work location and be able to work in person regularly.
Nice To Haves
- Experience with RAG pipelines and vector databases.
- Experience with LLM observability and evaluation tools.
- Exploratory data analysis experience.
- MLOps/LLMOps practices.
Responsibilities
- Design and build multi-agent AI workflows from concept through deployment.
- Integrate foundation models through APIs and orchestration frameworks.
- Engineer and refine prompts and agent instructions.
- Build testing and evaluation strategies for AI outputs.
- Collaborate with engineers and domain experts and present tradeoffs.
- Apply existing large language models to mission workflows to automate manual work and streamline reporting.
Benefits
- 10% employer 401(k) non-elective contribution.
- Employer-paid life insurance.
- Employer-paid short- and long-term disability insurance.
- Medical, dental, and vision coverage options.
- Employee Assistance Program.
- Professional development and certification reimbursement.
- Technology and ergonomic equipment reimbursement, subject to eligibility.
- Referral and retention bonus programs, subject to eligibility.
- Paid social and team events.
- Compensation model options include a five-weeks-of-PTO option; PTO depends on the selected model and role eligibility.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Mid Level
