About the role
You will build and harden the AI core of NGCI's governed platforms — ProposalForge, TalentFlow, SectorAI, and the NGOS operating spine. This is production AI engineering: retrieval pipelines over approved knowledge, model integrations behind a governance gateway, and evaluation harnesses that prove quality before anything reaches a user. You will work on-site with client teams, seeing exactly how your systems perform in real workflows.
What you'll do
- Design and build retrieval-augmented generation (RAG) pipelines over governed document corpora — ingestion, chunking, embeddings, vector search, and relevance tuning.
- Integrate LLMs behind NGCI's AI governance gateway — policy checks, redaction, audit logging, and human-approval workflows around every model call.
- Build evaluation harnesses and regression suites that measure answer quality, grounding, and drift — and gate releases on them.
- Tune prompt systems, routing, and model selection for cost and quality across multiple model tiers.
- Work with delivery teams on client sites to adapt platforms to real workflows, data, and security requirements.
- Document designs and decisions to NGCI engineering standards — everything on the record.
What we're looking for
- 3+ years of professional software engineering with strong Python.
- Hands-on experience shipping LLM-backed features to production — not just prototypes.
- Working knowledge of retrieval systems: embeddings, vector stores, and search relevance.
- SQL and data-modeling fundamentals (we run on PostgreSQL).
- Clear written communication — you can explain a design and defend a tradeoff.
- Authorization to work in the United States.
Nice to have
- Experience with AWS (Bedrock, ECS/Lambda, IAM) or comparable cloud AI stacks.
- Evaluation frameworks, guardrails tooling, or AI red-teaming experience.
- Prior work in regulated or public-sector environments.
- FastAPI, React, or full-stack exposure.
About NGCI
NextGen Consulting Inc. (NGCI) has delivered public-sector technology — ERP, cloud, cybersecurity, data, and integration — since 2006, and now builds governed AI platforms on the same operating discipline: AI assists, humans approve, everything on the record. You would join a team that runs its own company on the systems it sells.
At a glance
- Req. number
- NGCI-26-0001
- Location
- College Park, MD
- Work mode
- On-site
- Job type
- Full-time
- Clearance
- None stated in this posting
- Posted
Eligibility
Some government roles may require the ability to obtain a public-trust or security clearance; the posting conversation will make that clear before you invest time.
How hiring works
- Apply below — a human reads it.
- 30-minute intro call.
- Role-specific deep-dive on real problems.
- Clear decision, with feedback.
Compensation is discussed early in the process, before you invest significant time.
Apply
Apply for this role
What happens next
- A human reviews your application — typically within one week.
- If there's a fit, we schedule a 30-minute intro call.
- If not now, we keep strong candidates in mind for future roles.
Equal opportunity
NGCI is an equal opportunity employer. We evaluate applicants without regard to race, color, religion, sex, national origin, age, disability, veteran status, or any other protected characteristic. If you need an accommodation during the hiring process, tell us in your application and we'll make it work.
Some government roles may require the ability to obtain a public-trust or security clearance; the posting conversation will make that clear before you invest time.