Build the data pipelines, knowledge bases, and AI components behind secure generative AI applications for a U.S. Government client, and support the people who use them.
This is a hybrid role in the Washington, DC metro area, on site at Government offices three days a week.
You will build and maintain the data pipelines, retrieval-augmented generation (RAG) knowledge bases, and AI services that power secure AI applications, help automate how they are deployed, and serve as a helpdesk resource for application users.
What you'll do
- Build and maintain ETL/ELT pipelines that prepare structured and unstructured content for AI workloads
- Create and refresh RAG knowledge bases, including document chunking, embeddings, and vector indexing
- Develop Python services, APIs, and LLM integrations with guidance from senior engineers
- Maintain CI/CD and model-lifecycle pipelines with automated testing, security scanning, and TEVV checkpoints
- Curate and version datasets with lineage tracking, data-quality checks, and PII masking
- Write unit and integration tests, support model evaluations, and document defects
- Monitor pipelines and indexes, troubleshoot failures, and support incident response
- Resolve helpdesk tickets from application users and escalate issues when needed
- Write user manuals, job aids, and technical documentation, and keep code in Government-approved repositories
What you'll bring
- Bachelor's degree in a related field and 1+ year of relevant experience (equivalent experience may substitute for the degree)
- 1+ year of hands-on Python development
- Experience with data pipelines, SQL, and relational or NoSQL databases
- Hands-on exposure to generative AI: LLM APIs, embeddings, vector databases, or RAG
- Familiarity with AWS, Azure, or Google Cloud, plus Git and CI/CD tools
- Technical or application support experience, including working with non-technical users
- U.S. citizen or lawful permanent resident
- Lives in the Washington, DC metro area and can work on site at Government offices three days a week
- Able to obtain and maintain a Public Trust background investigation
Nice to have
- 3+ years of software or data engineering experience, including work on federal agency programs
- Experience with RAG frameworks and vector stores
- Experience with OCR and PDF parsing, Docker or Kubernetes, and MLOps tools
- Experience with ITSM tools such as ServiceNow or Jira Service Management, or ITIL Foundation certification
- A generative AI or machine learning certification from a major cloud provider
- An active Public Trust or prior federal background investigation
NEXA Consulting LLC is an equal opportunity employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, or protected veteran status. Some positions require U.S. citizenship or the ability to pass a background investigation.