GenAI Engineer - Rapid Prototyping & RAG Pipelines

CACI International; Reston (VA); Presencial; USD 82 000 - 172 000; Tempo integral

Resumo da oferta

CACI is seeking an AI Engineer to join our AI Center of Excellence, delivering rapid, production‑level AI solutions across diverse programs in 1–2 month rotations. You will build RAG pipelines, deploy conversational AI platforms, and implement multi‑agent systems while leveraging a catalog of reusable templates and guardrails.

You’ll work in a fast-changing CTO environment, focusing on integration, observability, cost controls, and learning to scale AI across government missions with strong

Qualificações

• 3–5 years building production applications with Python/JavaScript, Git workflows, and modern development practices.
• Experience with LLM-powered apps, agent patterns, RAG, prompt engineering, vector databases, and observability concepts; hands-on experimentation preferred.
• Monitor AI performance (latency, cost, quality), address failure modes, and apply guardrails.
• Strong background designing, implementing, and troubleshooting RESTful and event-driven integrations.
• Experience with AWS/Azure/GCP, containerization, CI/CD, IaC, and secure API/key management.
• Understanding of basic ML concepts and their application to LLM systems.
• Proven ability to deliver solutions quickly in unfamiliar environments with evolving requirements.
• Strong communication skills and ability to document and teach complex AI concepts.
• Ability to make trade-offs under pressure and leverage reusable templates.
• Active user of modern AI tools; engagement with communities.
• Experience with GitLab, Jira, and iterative delivery.
• Ability to obtain and maintain a Top Secret clearance.

Responsabilidades

• Rapid AI Application Delivery: Produce production-ready AI solutions in 1–2 month rotations (RAG pipelines, conversational platforms, multi-agent systems).
• GenAI Implementation: Build custom AI solutions using vector databases, orchestration frameworks, and managed AI services with observability and security.
• Integration & Operationalization: Integrate LLM APIs into workflows, set guardrails, monitor and resolve cross-cloud issues.
• Knowledge Transfer & Enablement: Lead hands-on training, create docs, pair-program with teams for independence.
• Solution Catalog Contributions: Improve templates, document new patterns from field use.
• Operational Validation: Ensure teams reach full operational independence via structured handoffs.
• Continuous Learning: Explore GenAI tools and share insights through demos and docs.

Conhecimentos

Python

JavaScript

Git workflows

LLM-powered apps

RAG

vector databases

observability

RESTful APIs

event-driven integrations

AWS/Azure/GCP

containerization

CI/CD

IaC

secure API management

GitLab/Jira

Top Secret clearance

Ferramentas

Kubernetes

Terraform

GitLab

Jira

CI/CD pipelines

Vector databases

Descrição da oferta de emprego

CACI is seeking an AI Engineer to join our AI Center of Excellence, delivering rapid, production‑level AI solutions across diverse programs in 1–2 month rotations. You will build RAG pipelines, deploy conversational AI platforms, and implement multi‑agent systems while leveraging a catalog of reusable templates and guardrails.

You’ll work in a fast-changing CTO environment, focusing on integration, observability, cost controls, and learning to scale AI across government missions with strong