AI Engineer

CACI

Denver (CO)

On-site

USD 82,000 - 172,000

Full time

3 days ago

Be an early applicant

Application generator

An application made for this job — a tailored resume and cover letter that speak straight to the posting.

Get past ATS filters

Benefits offered by this job

Healthcare

Wellness

Financial

Retirement

Family support

Continuing education

Time off benefits

Competitive compensation

Learning & development opportunities

Job summary

CAСI is seeking an AI Engineer to deliver production-ready GenAI applications through short, rotational engagements in Denver, CO. You will build RAG pipelines, conversational platforms, and multi-agent systems, focusing on operationalization and reusable solution catalogs.

You’ll work with vector databases, orchestration frameworks, and managed AI services, ensuring observability, security, and cost controls while integrating LLM APIs across cloud/on-prem environments.

Qualifications

3–5 years building production applications with Python/JavaScript, Git workflows, and modern development practices.
Practical experience with LLM-powered apps, agent patterns, RAG, prompt engineering, vector databases, and observability concepts; hands-on experimentation preferred.
Ability to monitor AI performance (latency, cost, quality), address failure modes, and apply responsible AI practices such as bias detection and guardrails.
Strong background designing, implementing, and troubleshooting RESTful and event-driven integrations.
Experience with AWS/Azure/GCP, containerization, CI/CD, IaC concepts, and secure API/key management.
Understanding of basic ML concepts and how they apply to LLM systems.
Proven ability to deliver solutions quickly in unfamiliar environments with evolving requirements.
Strong communication skills, including creating clear documentation and teaching complex AI concepts.
Ability to obtain and maintain a Top Secret clearance.
Experience with GitLab and Jira, and iterative delivery.

Responsibilities

Deliver production-ready AI solutions in 1–2 month rotations, including RAG pipelines, conversational platforms, and multi-agent systems.
Build and customize AI solutions using vector databases, orchestration frameworks, and managed AI services, with observability, security, and cost controls.
Integrate LLM APIs and AI services into workflows, apply guardrails, configure monitoring/alerting, and troubleshoot across cloud and on‑prem environments.
Lead hands‑on training, create documentation, and pair-program with teams to enable independent operation and evolution of AI apps.
Improve templates, document reusable patterns, and capture new techniques from field experience.
Ensure operational independence through structured handoff and validation processes.
Explore emerging GenAI tools, evaluate federal use‑case applicability, and share insights via demos & docs.

Skills

Python/JavaScript

Git workflows

LLM-powered apps

Agent patterns

RAG

Prompt engineering

Vector databases

Observability concepts

RESTful integrations

Event-driven integrations

AWS/Azure/GCP

Containerization

CI/CD

IaC concepts

Secure API/key management

ML concepts

Documentation/knowledge transfer

GitLab

Jira

Top Secret clearance

Tools

Kubernetes

Terraform

React

FastAPI

GitLab

Jira

AWS Bedrock

Azure OpenAI

CI/CD pipelines

Containerization

Job description

CAСI is hiring an AI Engineer to support its AI Center of Excellence, delivering production-ready GenAI applications through short, rotational engagements. The work includes building RAG pipelines, conversational AI platforms, and multi-agent systems, with an emphasis on operationalization, knowledge transfer, and improvement of a reusable solution catalog.

Responsibilities

Deliver production-ready AI solutions in 1–2 month rotations, including RAG pipelines, conversational platforms, and multi-agent systems, tailored to each program’s mission and technology stack.
Build and customize AI solutions using vector databases, orchestration frameworks, and managed AI services, while implementing observability, security, and cost controls.
Integrate LLM APIs and AI services into existing workflows, apply responsible AI guardrails, configure monitoring/alerting, and troubleshoot integration issues across cloud and on-prem environments.
Lead hands‑on training, create documentation, and pair-program with teams to support independent operation and ongoing evolution of AI applications.
Improve existing templates, create reusable patterns, and document new techniques based on field experience.
Confirm operational independence through structured handoff and validation processes.
Explore emerging GenAI tools, evaluate federal use‑case applicability, and share insights through demos and documentation.

Required Qualifications

3–5 years building production applications with Python/JavaScript, Git workflows, and modern development practices.
Practical experience with LLM-powered apps, agent patterns, RAG, prompt engineering, vector databases, and observability concepts; hands‑on experimentation preferred.
Ability to monitor AI performance (latency, cost, quality), address common failure modes, and apply responsible AI practices such as bias detection and guardrails.
Strong background designing, implementing, and troubleshooting RESTful and event‑driven integrations.
Experience with AWS/Azure/GCP, containerization, CI/CD, IaC concepts, and secure API/key management.
Understanding of basic ML concepts and how they apply to LLM systems.
Proven ability to deliver solutions quickly in unfamiliar environments with evolving requirements.
Strong communication skills, including creating clear documentation and teaching complex AI concepts.
Ability to make trade‑offs under pressure, prioritize working solutions, and leverage reusable templates.
Active user of modern AI tools, staying current through experimentation and community engagement.
Experience with GitLab, Jira, and iterative delivery.
Ability to obtain and maintain a Top Secret clearance.

Preferred Qualifications

Experience deploying agentic AI systems, using observability tools, vector databases, guardrails, embeddings, and structured outputs.
AWS (Bedrock/GovCloud), Azure OpenAI, Kubernetes, Terraform, and CI/CD pipeline experience.
Proficiency in JS/TS/Python for front‑end/back‑end development and modern frameworks such as React or FastAPI.
Experience leading client engagements, context‑switching across projects, and delivering strong knowledge transfer.
Familiarity with DoD/federal missions, security requirements, and compliance frameworks (including ATO and NIST).
History of open‑source work, technical writing, conference speaking, or similar community involvement.
Security+ , AWS certifications, or other relevant technical credentials.