First seen by Alion on Nov 20, 2026.
Artificial Intelligence (AI) Engineer - IT Consultant 1
Company: Stealth Entry Cybersecurity Solutions
Client: State of Ohio, Ohio
Location: 100% onsite, 5 days a week, at 50 W. Town Street, Columbus, OH 43215
Work Hours: Monday through Friday, 8:00 a.m. to 5:00 p.m. EST
Engagement: 1-year contract with the possibility of an extension
Eligibility: U.S. Citizens and Green Card holders only. Candidates local to Columbus, Ohio preferred.
Interviews: Conducted onsite
About Stealth Entry
Stealth Entry Cybersecurity Solutions is a Service-Disabled Veteran-Owned Small Business and Ohio Minority Business Enterprise headquartered in Westerville, Ohio. We provide skilled IT and cybersecurity professionals to federal, state, and commercial clients.
About the Role
Stealth Entry is hiring an experienced AI Engineer for our client, the State of Ohio, to support the Ohio Department of Medicaid. You will design, build, deploy, and support enterprise-grade AI solutions on ODM’s existing AI and cloud ecosystem, including Google Vertex AI, Gemini models, GitHub Copilot, and cloud-native services. The work includes production-ready AI applications, Retrieval Augmented Generation (RAG) architectures, agentic workflows, document intelligence pipelines, and AI-powered assistants. You will also serve as a trusted technical advisor, helping agency leadership weigh technology options, risks, costs, and benefits. This is a senior, hands-on role that calls for strong independent technical judgment.
What You’ll Do
Enterprise AI Solution Design and Development
- Design, build, deploy, and maintain scalable, secure, production-ready AI applications. This includes intelligent automation workflows, document intelligence solutions, and advanced analytics.
- Architect and optimize end-to-end RAG systems, covering:
- context management
- document chunking
- embedding generation
- vector database search
- Design and orchestrate agent-based architectures and multi-step workflows that integrate with enterprise applications, APIs, databases, and cloud services.
- Engineer and manage structured prompts using modern prompt engineering and prompt management frameworks, so outputs are reliable and accurate.
Model Strategy, Optimization, and Evaluation
- Implement dynamic model selection and routing that matches each workload to the best model for its complexity, accuracy, latency, and cost needs.
- Apply token optimization and resource utilization techniques to reduce operating cost and inference latency while preserving response quality.
- Build and run AI evaluation frameworks, automated benchmarking pipelines, and response quality metrics before and after production release.
AI Governance, Security, and Production Operations (LLMOps)
- Implement Responsible AI controls, security guardrails, and hallucination mitigation techniques suited to healthcare and public-sector compliance.
- Apply data privacy protections, including PII/PHI safeguards.
- Establish and maintain CI/CD and MLOps/LLMOps pipelines for automated testing, deployment, monitoring, observability, and lifecycle management of AI services.
- Troubleshoot, debug, and optimize AI applications in production to keep them available and accurate.
- Support ongoing and recurring IT security audits of AI systems.
Technical Leadership and Advisory
- Consult with ODM business and program/project management teams to define requirements and recommend appropriate technical solutions.
- Evaluate emerging AI technologies, frameworks, and tools for practical fit and ROI, and track industry trends to upgrade agency systems.
- Advise on industry alternatives, options, risks, costs versus benefits, and impact on other business processes and system priorities.
- Establish agency-wide AI engineering standards, reusable framework components, and architectural best practices.
- Provide technical leadership, code and design reviews, and mentorship to engineering teams adopting AI and developer productivity tools such as GitHub Copilot.
Required Qualifications
- Bachelor’s degree in Computer Science, Artificial Intelligence, Data Science, Software Engineering, Engineering, or a related field, or equivalent progressive experience.
- 5+ years of hands-on software engineering experience building and deploying production enterprise applications.
- 2+ years of recent, hands-on experience designing, developing, deploying, and maintaining Generative AI/LLM solutions in enterprise cloud environments.
- Practical experience with Google Cloud Vertex AI and Gemini models.
- Deep proficiency in:
- embeddings
- vector databases
- semantic and hybrid search
- chunking strategies
- context window management
- Hands-on expertise in prompt engineering, model routing and orchestration frameworks, agent-based workflows, and structured output generation.
- Proven experience with automated LLM evaluation and benchmarking, telemetry and observability, hallucination reduction, and AI security and privacy guardrails.
- Strong Python skills and modern software engineering practices, including:
- REST and event-driven APIs
- cloud-native infrastructure
- containerization
- CI/CD pipelines for the AI lifecycle
- Ability to work onsite in Columbus, Ohio, 5 days a week.
Preferred Qualifications
- Experience with GitHub Copilot in enterprise engineering workflows.
- Experience in an IT department or consulting company, with broad exposure across technology areas.
- Experience with healthcare, Medicaid, or public-sector systems and compliance (HIPAA, PII/PHI).
Core Competencies
- Strong independent judgment in balancing accuracy, response quality, latency, security, and cost.
- Analytical problem-solving to diagnose non-deterministic model behavior and distributed-system bottlenecks in production.
- Clear communication of AI capabilities, trade-offs, and risk mitigation to both technical teams and agency leadership.

