Job Title
Senior Azure Data Architect
Job Type
Full-time
Category
Information Technology
Location
FAIRFAX - , VA 22030 US (Primary)
Education
Bachelor's Degree
Travel
Job Description
A federal agency already runs a production AI Assistant on Azure Government. You will be the technical authority who extends it to the case files, case records and legal documents of three more of its offices, so that an attorney or investigator gets a cited answer in seconds and never sees a page their role is not cleared to see. Full time, W-2, starting 19 October 2026.
The environment you will work inYou inherit a working stack and you build inside it. The agency operates the platform; you own what SPN builds on it.
- Azure Government, with separate dev and test subscriptions and production behind an agency go decision
- A governed PostgreSQL read replica fed by change data capture from the agency's case system
- A dbt semantic layer and a data catalog
- Approved Azure OpenAI services, a platform vector store, OCR and embedding services
- Apache Superset for dashboards and AI-assisted views
- A production AI Assistant with retrieval guardrails already in place
- The agency's Git repositories and CI/CD runners, where all code lives from the first commit
- Python: pandas, SQLAlchemy, psycopg, the Azure OpenAI SDK and test frameworks
What you will do- Own the technical design of every product and record each design decision in the agency repository
- Register each office's case tables and document sets as sources, with a freshness expectation for each
- Check every document for a native text layer and send only image pages to OCR
- Hold pages below the agreed OCR confidence in a review queue instead of indexing them
- Split text on headings, numbered paragraphs, exhibits and pages, and tag every chunk with its document, page, case, owning office and role scope
- Keep the index current from the change stream, removing deleted, withdrawn and redacted material explicitly
- Configure hybrid lexical and vector retrieval with rank fusion, suppress any sentence without a supporting source, and refuse when the evidence is weak
- Compile each user's identity claims into a mandatory filter on every vector query, and write PostgreSQL row-level security and field masking by role
- Write an audit record for every retrieval and export
- Measure retrieval recall, citation precision, groundedness, refusal correctness and access correctness against the agency's test set at every acceptance test
- Build the CI/CD path that promotes dbt, Python and Superset assets from dev to test to production, with a probe that checks upstream schema and credentials before every scheduled run
- Supply the configuration evidence and test results behind the NIST SP 800-53 control statements, and fix penetration-test findings on what we build
Your first 90 days- Days 1 to 30: suitability forms filed on day one; source inventory and design for the first office; access-control design reviewed with the agency
- Days 31 to 60: the first office's content extracted, chunked and embedded in dev, returning cited answers; the paired-role access test written
- Days 61 to 90: AI features running inside the first product in dev; first measurement run against the agency's test set; the product ready for user acceptance testing in month 4
How your work is judged- Zero unauthorized-access defects, proven by running the same query under paired roles before every promotion
- AI quality measures at or above the thresholds agreed with the agency, for every office
- No upstream change breaks a scheduled refresh without your probe raising it first
- Every security control statement backed by evidence you produced
What you need- United States citizenship, and the ability to obtain a Public Trust Tier 2 determination (the agency sponsors it)
- A bachelor's degree in computer science, information technology or a related field
- 12 or more years in technology, 8 or more of them in cloud and data architecture
- Azure architecture at the level of AZ-305, by certification or by equivalent hands-on work
- At least one document question-answering application with citations that you put into production, on Azure OpenAI or an equivalent
- PostgreSQL or SQL Server at the level of writing row-level security policies
- Python
- CI/CD in GitHub Actions or Azure DevOps
What sets a candidate apart- An active Public Trust, Tier 4 or Secret, which can shorten the start to one to three weeks through reciprocity
- CISSP or an equivalent senior security certification, or 5 or more years of security architecture
- Production OCR or Azure Document Intelligence pipelines
- Azure Government, pgvector or Azure AI Search
- Apache Superset or another open-source BI platform, and dbt
- Written NIST SP 800-53 control evidence for a Federal system
BenefitsPay is discussed with you directly when we speak. These are the benefits every full-time SPN employee receives.
- Medical and prescription coverage, dental and vision
- Short-term disability
- Life and accidental death insurance
- Competitive 401(k)
- 11 paid federal holidays
- Paid vacation
- Paid sick leave
- Parental leave
- Tuition and professional development assistance
Terms, and how to apply- Full time, W-2, salaried (exempt), employed by SPN Solutions
- Target start: 19 October 2026
- Hybrid, based in Fairfax, Virginia, with some days in Washington, DC when needed
- All customer work is done on a government-furnished laptop with a PIV credential
- SPN pays the exam fee for the Azure certifications tied to this role if you do not hold them
Apply through the link with your resume. A recruiter reads every application and answers within two business days. If you have built a cited question-answering system, tell us in two or three lines what it searched, who used it and how you kept people from seeing what they should not.
