AI Security Engineer

Perfict; Round Rock (TX); On-site; USD 120,000 - 190,000; Full time

Job summary

Perfict is seeking a seasoned AI/LLM engineer to design, deploy, and scale autonomous agent solutions in enterprise environments. You will own end-to-end delivery from requirements gathering to production adoption, emphasizing security, reliability, and measurable business impact.

You will build agentic workflows, multi-agent systems, and tooling integrations with enterprise platforms, APIs, and CI/CD pipelines, while mentoring teammates and promoting secure-by-default practices.

Qualifications

• Proven experience developing and deploying AI/LLM solutions into production environments.
• Hands-on experience building autonomous AI agents or agentic workflows for enterprise business.

Responsibilities

• Design, develop, test, and deploy AI-powered and autonomous agent solutions for enterprise workflows.
• Build agentic workflows, agent loops, multi-agent systems, sub-agents, and tool/calling capabilities.
• Translate business and stakeholder requirements into secure, scalable, and production-ready AI solutions.
• Take ownership of the complete solution lifecycle, including requirements gathering, architecture, development, testing, deployment, monitoring, and adoption.
• Develop AI capabilities that support the SDLC, including: AI-generated code assurance, Security guardrails and policy enforcement, Automated design and security reviews, Dependency and software supply-chain analysis, Static and dynamic analysis orchestration, Release and compliance audit support.
• Integrate AI solutions with enterprise platforms such as source control, CI/CD pipelines, ticketing systems, security scanning tools, identity platforms, cloud services, and internal applications.
• Develop integrations using REST/GraphQL APIs, webhooks, MCP (Model Context Protocol), and other enterprise protocols.
• Apply strong software architecture and systems-design principles, including service boundaries, data modeling, observability, scalability, extensibility, and secure defaults.
• Engineer effective context management, including retrieval, search, memory architectures, enterprise data grounding, and structured outputs.
• Optimize LLM token consumption, context windows, cost, latency, and overall production performance.
• Develop and implement AI evaluation practices to measure accuracy, reliability, safety, quality, and business impact.
• Evaluate emerging AI technologies, agentic frameworks, retrieval and memory systems, evaluation frameworks, guardrails, and LLMOps capabilities.
• Partner with security, engineering, product, architecture, and leadership teams to evaluate technical trade-offs and drive adoption.
• Establish reusable AI engineering patterns, standards, documentation, and best practices.
• Promote secure-by-design and secure-by-default principles throughout AI solution development.
• Mentor team members and contribute to technical enablement through documentation, demonstrations, and knowledge sharing.

Skills

AI/LLM solutions

Autonomous agents

Job description

• Design, develop, test, and deploy AI-powered and autonomous agent solutions for enterprise business and security workflows.
• Build agentic workflows, agent loops, multi-agent systems, sub-agents, and tool/function-calling capabilities.
• Translate business and stakeholder requirements into secure, scalable, and production-ready AI solutions.
• Take ownership of the complete solution lifecycle, including requirements gathering, architecture, development, testing, deployment, monitoring, and adoption.
• Develop AI capabilities that support the SDLC, including:
• AI-generated code assurance
• Security guardrails and policy enforcement
• Automated design and security reviews
• Dependency and software supply-chain analysis
• Static and dynamic analysis orchestration
• Release and compliance audit support
• Integrate AI solutions with enterprise platforms such as source control, CI/CD pipelines, ticketing systems, security scanning tools, identity platforms, cloud services, and internal applications.
• Develop integrations using REST/GraphQL APIs, webhooks, MCP (Model Context Protocol), and other enterprise protocols.
• Apply strong software architecture and systems-design principles, including service boundaries, data modeling, observability, scalability, extensibility, and secure defaults.
• Engineer effective context management, including retrieval, search, memory architectures, enterprise data grounding, and structured outputs.
• Optimize LLM token consumption, context windows, cost, latency, and overall production performance.
• Develop and implement AI evaluation practices to measure accuracy, reliability, safety, quality, and business impact.
• Evaluate emerging AI technologies, agentic frameworks, retrieval and memory systems, evaluation frameworks, guardrails, and LLMOps capabilities.
• Partner with security, engineering, product, architecture, and leadership teams to evaluate technical trade-offs and drive adoption.
• Establish reusable AI engineering patterns, standards, documentation, and best practices.
• Promote secure-by-design and secure-by-default principles throughout AI solution development.
• Mentor team members and contribute to technical enablement through documentation, demonstrations, and knowledge sharing.

Required Qualifications

• Proven experience developing and deploying AI/LLM solutions into production environments.
• Hands-on experience building autonomous AI agents or agentic workflows for enterprise business p