
Principal AI Engineer, Product Cybersecurity
Posted 3 days ago

Posted 3 days ago
This is a fully remote position, open to applicants in Texas.
• Develop and deploy prompts, agents, skills, tools, MCP servers, connectors, scripts, and orchestration logic for comprehensive LLM applications.
• Transform manual security processes into AI-assisted workflows for engineering analysis, knowledge retrieval, documentation, requirements analysis, code/design reviews, test generation, and security-assessment assistance.
• Establish secure connections between the AI harness and authorized customer documentation, knowledge sources, repositories, APIs, identity systems, and downstream tools.
• Create a reusable library of components to expedite the delivery of future use cases.
• Make and document practical design decisions regarding model integration, context management, and tool integration.
• Participate in design and code reviews to ensure the development of secure, maintainable, and reusable components.
• Develop evaluations and quality gates that encompass output quality, groundedness, hallucination rates, reliability, security, usefulness, latency, and costs.
• Analyze production transcripts and user feedback to enhance workflows.
• Version, test, deploy, monitor, and maintain prompts, contexts, and components.
• Design reliability features such as model fallback, graceful degradation, timeouts, and retries.
• Implement access controls, data handling procedures, traceability, and guardrails through change-management and security review processes.
• Collaborate with team members and customer engineers to identify high-value AI tasks, build solutions together, and mentor engineers through examples and documentation.
• Bachelor's degree in Computer Science, Engineering, or a related field, or equivalent practical experience.
• 8+ years of professional software development experience, with a proven ability to write, ship, and maintain production software.
• Strong software engineering fundamentals: version control, code review, automated testing, debugging, and maintainable design.
• Hands-on experience in building LLM-powered applications or AI-assisted workflows, including prompting and context engineering, retrieval (RAG), agent and tool-use frameworks, and evaluation; production experience is highly preferred.
• Practical familiarity with model APIs from at least one major provider (Anthropic, OpenAI, Google, or an equivalent open-weight model).
• Experience with cloud platforms (AWS, Azure, or GCP), containerization, and CI/CD practices.
• Proven experience in designing secure systems, including access controls, data handling, traceability, and guardrails for sensitive data.
• Ability to rigorously reason about non-deterministic systems and understand the distinction between a successful demo and a successful test.
• Excellent written and verbal communication skills; capable of articulating trade-offs to both engineers and executives.
• Background in developing agentic AI systems, including tool usage, workflow orchestration, multi-step autonomous workflows, and human-in-the-loop patterns.
• Experience with MCP, agent orchestration frameworks, and observability/tracing for LLM applications.
• Background in Product Cybersecurity, application security, or security-assessment workflows.
• Experience in defining evaluation frameworks for AI output quality, reliability, and safety.
• Familiarity with MLOps/LLMOps practices for versioning, deploying, monitoring, and maintaining AI systems.
• Understanding of AI governance and risk frameworks (NIST AI RMF, ISO/IEC 42001, EU AI Act) and secure handling of sensitive data in AI systems.
• Experience in conducting technical workshops, pairing, or mentoring engineers who are new to AI.
• Competitive salary and performance-based bonuses.
• Comprehensive health and wellness benefits.
• Opportunities for professional development and continuous learning.
• Flexible work arrangements and a supportive work environment.
Extend
OhioHealth
Capital One
Software Mind
Get handpicked remote jobs straight to your inbox weekly.