AI/ML SOFTWARE ENGINEER with Security Clearance

ASD; Chandler (AZ); On-site; USD 120,000 - 180,000; Full time

Job summary

ASD in Chandler, AZ seeks a highly motivated AI / Automation Engineer to design, develop and deploy AI-enabled automation that integrates LLM services into engineering workflows. You will build agent orchestration, RAG pipelines, and containerized apps for on-premise environments, with emphasis on reliability and maintainability.

You will work across DevOps and mission stakeholders, implement CI/CD pipelines, and ensure observability, performance, and secure deployments in classified settings.

Qualifications

• Bachelor’s degree with 2+ years of professional experience, or Master’s with 1+ year, or PhD with 1+ year.
• Ability to obtain and maintain U.S. Government DoD Secret security clearance.
• Hands-on experience deploying LLM-enabled applications and agentic workflows.
• Experience with APIs, LLM services, and agent orchestration frameworks.
• Familiarity with LangChain, Mastra or equivalent toolchains.
• Experience with Docker and orchestration platforms (Kubernetes/OpenShift).
• Experience deploying AI/ML apps in on-premise/containerized environments; cloud experience valued.

Responsibilities

• Design, develop, document, test, and debug AI-enabled automation capabilities.
• Build and deploy agent orchestration frameworks and RAG solutions with vector DB integrations.
• Support containerized environments across on-premise and classified settings.
• Troubleshoot deployments, improve observability, availability, and performance.
• Develop and maintain CI/CD pipelines and automated deployment workflows.
• Collaborate with software, DevOps, infrastructure, and mission stakeholders.

Skills

LLM deployment

Python

Go (Golang)

Docker

Kubernetes

CI/CD

Linux scripting

RAG pipelines

Observability

APIs

Education

Bachelor’s degree (STEM)

Master’s degree (STEM)

PhD (STEM)

Tools

LangChain

Mastra

GitLab

Jenkins

OpenShift

Job description

We are seeking a highly motivated AI / Automation Engineer to join our dynamic team. In this role, You will design, develop, deploy, and support AI-enabled automation solutions that integrate existing LLM and agentic capabilities into engineering and infrastructure workflows. The role emphasizes bringing AI-enabled tools into operational use in on-premise and classified environments. This role sits at the intersection of AI, automation, CI/CD, and infrastructure, giving you the opportunity to: Build and integrate AI-enabled automation capabilities into engineering workflows

Deploy and support LLM-enabled, agentic, and RAG-based solutions

Enable reliable delivery through containerization, CI/CD, and infrastructure support

Join us and be part of a team driving innovative solutions at the forefront of space systems and advanced software! Your Role and Impact In this role, you will: Design, develop, document, test, and debug AI-enabled automation capabilities that integrate existing LLM services, APIs, and engineering tools into operational workflows.

Build, deploy, and support agent orchestration frameworks and Retrieval-Augmented Generation (RAG) solutions, including integrations with vector databases and enterprise data sources.

Support containerized, on-premise and classified environments at scale, with cloud-based deployment exposure also valued.

Troubleshoot deployed AI and automation solutions, resolve integration and performance issues, and improve observability, availability, and maintainability over time.

Develop, deploy, and maintain containerized applications using Docker or comparable container technologies, with attention to load balancing, virtual-machine resource utilization, and system performance.

Build and maintain CI/CD pipelines, version-control practices, and automated deployment workflows that enable reliable delivery of AI-enabled tools and services.

Partner with software, DevOps, infrastructure, and mission stakeholders to identify automation opportunities and transition solutions into production use.

Provide infrastructure support by resolving container, system-performance, resource-utilization, and availability issues that affect deployed solutions.

Communicate clearly with technical and non-technical stakeholders, both in writing and verbally.

Perform other related duties as assigned.

If this job description reads like it was written specifically for you, we’d like to talk with you.

Basic Qualifications for Level 2: Bachelor’s degree with 2 years of professional experience – OR – Master’s degree with 1 years of professional experience – OR – PhD with 1 year of professional experience. Must have the ability to obtain and maintain a U.S. Government DoD Secret security clearance.

Hands-on experience integrating and deploying LLM-enabled applications, including model hosting, agentic workflows, RAG, and inference considerations. Experience with advanced fine-tuning and inference optimization is preferred and may be developed in the role Experience integrating APIs, LLM services, and agent orchestration frameworks into applications or operational workflows. Experience with LangChain, Mastra, or comparable toolchains is welcome

Experience with Docker or comparable container technologies is required. Experience with orchestration platforms such as Kubernetes or OpenShift is beneficial

Experience developing, hosting, or supporting AI/ML applications in on-premise containerized environments; cloud-based deployment experience is also valued

Working knowledge of CI/CD, version control, automated deployment practices, and infrastructure fundamentals. Experience with tools such as GitLab, Jenkins, or similar platforms is preferred

Hands-on experience working in Linux environments, including scripting and system configuration.

Proficiency in Python or Go (Golang) with a strong background in software development, debugging, and testing.

Experience with Retrieval-Augmented Generation (RAG) pipelines and vector databases.

Strong working understanding of LLM deployment considerations, including hosting, inference, and operational reliability.