Generative AI Data Engineer
*The work*
We are seeking to build a team to implement LLM models into our current analytic environment. This role ranges from Senior to Junior level Software/Data Engineers to provide hands-on application engineering: agent orchestration, retrieval pipelines, tool integration, and the backend services that hold it together, deployed into a classified enterprise environment.
*What you’ll do*
Work varies with experience, but expect a mix of:
_Build agent components._ Implement orchestration logic, tool integrations, and memory handling within agent-based applications with design support early on and increasing ownership as you go.
_Work the retrieval pipeline._ Document processing, embedding generation, retrieval configuration, prompt assembly. This is where most people learn what actually makes RAG work, and where you’ll spend real time.
_Write the services._ Python REST APIs supporting data retrieval, system integration, and agent workflows.
_Handle the data._ Process and transform structured and unstructured data for AI workflows; work with Postgres schemas and query performance.
_Ship to production._ Testing, deployment, and the enterprise realities of a classified environment.
*Junior-level*
We’re looking for a working software engineer who wants to move into AI. You should bring:
- Solid Python, with real production code behind you
- Experience building or consuming REST APIs
- Comfort with databases and SQL
- _Some_ hands-on exposure to LLMs or a RAG prototype, an agent you wired up, a side project, a course. Curiosity you can point at, not a credential
- Bachelor’s in computer science or a related field (additional experience considered in lieu)
You do not need prior professional AI work. We’ll teach the domain.
*Mid-level*
Same foundation, plus you’ve shipped something AI-enabled:
- Hands-on work building LLM-integrated applications, RAG workflows, or retrieval-based systems
- Working familiarity with agent concepts for at least one AI framework
- Understanding of the fundamentals: how transformers behave, why context windows matter, where retrieval breaks down
- Enough production experience to have opinions about reliability and maintainability
*Senior-level*
You will design and lead the team to provide end to end orchestration within the platform.
- 8+ years of software engineering experience overall with recent hands-on work building AI/ML applications
- Bachelor’s in computer science or a related field
- Strong Python and fluency with common data and AI libraries
- Demonstrated experience with LLM-integrated applications, RAG workflows, or similar retrieval-based systems
- Working knowledge of agent-based programming
- Solid grounding in the fundamentals: transformers, LLM behavior, data processing, model integration patterns
- Experience designing or integrating REST APIs
- Production engineering habits: testing, reliability, deployment
*Must have *
- *Active TS Clearance*
*Nice to have*
- Elasticsearch optimization
- Docker and containerized development
- MCP or similar agent-to-tool protocols
Pay: $120,000.00 - $210,000.00 per year
Benefits:
- 401(k)
- 401(k) matching
- Dental insurance
- Employee assistance program
- Employee discount
- Flexible schedule
- Flexible spending account
- Health insurance
- Health savings account
- Life insurance
- Paid time off
- Parental leave
- Professional development assistance
- Referral program
- Tuition reimbursement
- Vision insurance
Security clearance:
- Top Secret (Required)
Work Location: In person