Skip to main content
G

Senior AI Engineer

GTN Solutions
5 hours ago
Full-time
On-site
Las Vegas, Nevada, United States
Senior AI Engineer Remote (PST/MST preferred) Contract with the ability to move to perm within 6-12 months

Essential Duties & Responsibilities Design and implement security controls for AI solutions across development, evaluation, deployment and inference environments, including hosted and third-party models. Build and deploy AI agents in Microsoft Foundry that integrate with Microsoft Sentinel, Azure Logic Apps, ServiceNow, Microsoft Fabric and external threat intelligence sources. Build and maintain secure reference architectures for generative AI (GenAI) and agent-based solutions. Design, develop, test and maintain AI agents and multi-agent workflows that automate security, business and technical processes. Develop agents that can reason, plan, retrieve information, call APIs and interact with enterprise applications. Implement tool/function calling, structured outputs, workflow orchestration, memory, context management and human-in-the-loop approvals. Implement retrieval-augmented generation (RAG) using structured and unstructured enterprise data. Build agent integrations using REST APIs, SDKs, event-driven architectures and enterprise integration patterns. Build and secure Model Context Protocol (MCP) integrations between agents and enterprise data and tools, using read-only defaults, managed identities, RBAC and least-privilege tool scopes. Develop reusable agent components, tools, prompts, connectors and services for use across AI initiatives. Manage agent code, prompts and configuration in GitHub, using CI/CD and source control integration with Fabric and Foundry. Implement least privilege, network segmentation, secrets management, encryption and secure configuration baselines for AI workloads. Implement strong identity and access controls for model endpoints, agents, tools, datasets and data pipelines. Identify and mitigate AI-specific threats, including: Prompt injection and indirect prompt injection, tool misuse and excessive agent permissions or autonomy, data/model poisoning, model extraction, model inversion, membership inference, and sensitive data leakage via prompts, outputs, logs, embeddings or telemetry Define and enforce AI guardrails through policy, technical controls and monitoring. Ensure secure handling of prompts, completions, embeddings and conversation memory. Establish AI evaluation, testing and monitoring for accuracy, safety, cost and performance. Evaluate emerging AI standards, frameworks and agent technologies, and recommend their adoption.

Qualifications Proof of authorization to work in the United States. Bachelor’s degree in Computer Science or related field 3+ years of experience in agentic development 5+ years of cyber or network security Must be able to obtain and maintain any certification or license, as required by law or policy. Experience in at least 4 of the following: o Software development o Network Administration o Programming experience in Python, Node, Typescript/JavaScript, C# o CI/CD pipelines o Network architecture o Git based source control o Large language models o Prompt engineering o Tool/Function calling o Vulnerability and security configuration scanning o Vulnerability and configuration exploit software o Agent orchestration o GitHub actions and/or Azure DevOps o AI Evaluation and testing o Secure configuration management o Threat intelligence o Metrics development Must be able to create and document network and system diagrams Must be able to write understandable procedures Must be able to respond to calls as needed (24/7) Must be able to design, install and implement cyber infrastructure solutions that integrate with the existing infrastructure