Job Description

Public Trust: None

Requisition Type: Pipeline

Your Impact

Own your opportunity to support our nation's defense. Make an impact by connecting and securing critical operations across the globe, keeping our country safe and secure.

Job Description

Join GDIT and be a part of the team of men and women that solve some of the world's most complex technical challenges. The CDAO Advana team is seeking an Site Reliability Engineer - Model Serving, to join their efforts in the DC area.

Advana is the Chief Digital and Artificial Intelligence Office’s (CDAO) enterprise-wide, multi-domain data, analytics, and artificial intelligence (AI) platform that provides all DoW military and civilian decision makers, analysts, and builders with unprecedented access to enterprise data, tools, and capabilities.

This is a proposal with award expected June 2026. If interested, please apply as we are interviewing and making contingent offers now.

Duties include:

Site Reliability Engineering Lead - Model Serving SME - Owns production reliability strategy for artificial intelligence and machine learning model serving across Advana enclaves supporting Department of Defense missions, Joint Staff analysts, Combatant Command elements, and Senior Executive Service leadership.

• Defines service‑level objectives, alerting philosophy, operational runbooks, and release safety patterns governing production deployment of model artifacts across multiple security domains.
• Establishes reliability governance across serving surfaces by developing operational standards, on‑call expectations, escalation pathways, and incident response patterns aligned with enterprise DevSecOps practices.
• Implements reliability engineering methodologies using Kubernetes, Prometheus, Grafana, Elastic Stack, GitLab Continuous Integration, VMware environments, and hardened deployment pipelines to maintain operational stability, mission assurance posture, and cross‑domain readiness.
• Develops automated reliability checks integrated into deployment workflows to validate performance, latency, availability, and operational suitability of production‑ready models.
• Leads coordination with Platform One, Cloud One, multi‑national engineering teams, and cross‑service mission partners to align reliability strategy with evolving architectures, security requirements, and mission priorities.
• Produces mission‑critical deliverables including service‑level objective documentation, alerting configurations, operational runbooks, reliability scorecards, incident post‑action reports, and release safety assessments.
• Strengthens program value by advancing operational readiness, reducing mission risk, and reinforcing deployment consistency across all enclaves. Supports Tier‑4 incident response actions by maintaining authoritative reliability artifacts required for rapid triage, operational continuity, and sustained mission performance.

Basic Qualifications:

• BS degree; additional years of experience may be considered in lieu of degree
• 8+ years of experience with production reliability strategy for artificial intelligence and machine learning model serving
• IAT II - Security+
• TS with SCI eligibility

WHAT CAN GDIT OFFER YOU?

• Excellent customizable health benefits (Medical, Dental and Vision)
• 401K with company match
• Educational Assistance and eLearning
• Flexible work week
• Internal mobility team dedicated to employee advancement
• Rewards and Recognition programs
• Innovative and collaborative environment encouraging of highly motivated critical thinking

Work Requirements

Years of Experience

8 + years of related experience

* may vary based on technical training, certification(s), or degree

Certification

CompTIA Security+ CE | CompTIA - CompTIA

Travel Required

None

Citizenship

U.S. Citizenship Required

Job Tags

Similar Jobs