Principal AI Engineer, Product Cybersecurity

Toyota Tsusho Systems•Plano, TX

About The Position

The Product Cybersecurity Group is building an AI harness that brings generative and agentic AI capabilities to Product Cybersecurity engineering. This hands-on engineering role builds prompts, agents, tools, connectors, and workflows that enable AI to perform practical Product Cybersecurity work across team workflows and customer environments. The engineer spends most of their time writing, testing, and shipping code with the team rather than producing architecture documents for others to implement. The role does not train foundation models; it adapts existing models into useful, reliable, measurable applications by building the full path from prototype to production, including data access, orchestration, evaluation, and observability for security-sensitive environments. The Principal AI Engineer brings software development discipline to AI work, including version control, code review, testing, debugging, and maintainable design. The role partners with engineers to turn security tasks into working AI-assisted workflows and helps team members learn to build and extend those workflows. The position involves building end-to-end LLM applications and reusable components; securely connecting approved documentation, knowledge sources, repositories, APIs, identity systems, and downstream tools; shaping practical technical decisions; and evaluating and operating deployed workflows. The engineer contributes to reviews, measures quality and operational performance, analyzes production transcripts and user feedback, and implements reliability and security practices in alignment with internal and customer requirements. The role also involves pairing with team members and customer engineers, explaining appropriate AI use and constraints, and teaching through clear examples and documentation.

Requirements

  • Bachelor's degree in Computer Science, Engineering, or a related field, or equivalent practical experience.
  • At least 8 years of professional software development experience, with a track record of personally writing, shipping, and maintaining production software.
  • Advanced software engineering and application development expertise.
  • Solid software engineering fundamentals, including version control, code review, automated testing, debugging, and maintainable design.
  • Hands-on experience building LLM-powered applications or AI-assisted workflows, including prompt and context engineering, retrieval-augmented generation, agent and tool-use frameworks, and evaluation; production experience is strongly preferred.
  • Practical experience with model APIs from at least one major provider: Anthropic, OpenAI, Google, or an open-weight equivalent.
  • Cloud experience with AWS, Azure, or GCP, as well as containerization and CI/CD.
  • Experience designing secure systems, including access controls, data handling, traceability, and guardrails for sensitive data.
  • Ability to evaluate, troubleshoot, and improve complex AI-enabled workflows using measurable performance criteria.
  • Ability to reason rigorously about non-deterministic systems and understand why a passing demo is not equivalent to a passing test.
  • Strong written and verbal communication skills, including the ability to explain technical concepts, risks, and tradeoffs to technical and non-technical audiences, including engineers and executives.
  • Ability to collaborate effectively across cross-functional teams and mentor engineers through hands-on development and knowledge sharing.
  • Demonstrated critical thinking, innovation, sound judgment, and ability to solve complex technical problems in security-sensitive environments.
  • Strong knowledge of generative AI, agentic AI systems, prompt engineering, context engineering, retrieval-augmented generation, and LLM application development.

Nice To Haves

  • Experience building 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 or tracing for LLM applications.
  • Background in Product Cybersecurity, application security, or security-assessment workflows.
  • Experience defining evaluation frameworks for AI output quality, reliability, and safety.
  • Familiarity with MLOps or LLMOps practices for versioning, deploying, monitoring, and maintaining AI systems.
  • Familiarity with AI governance and risk frameworks, including NIST AI RMF, ISO/IEC 42001, and the EU AI Act, and with secure handling of sensitive data in AI systems.
  • Experience running technical workshops, pairing, or mentoring engineers who are new to AI.

Responsibilities

  • Build and ship prompts, agents, skills, tools, MCP servers, connectors, scripts, and orchestration logic for end-to-end LLM applications, including retrieval pipelines, agent workflows, and structured-output workflows.
  • Turn manual security tasks into AI-assisted workflows for engineering analysis, knowledge retrieval, documentation, requirements analysis, code and design review, test generation, and security-assessment support.
  • Securely connect AI workflows to approved customer documentation, knowledge sources, repositories, APIs, identity systems, and downstream tools.
  • Build a reusable library of components to accelerate delivery of future use cases.
  • Make and document practical design decisions about model integration, context management, and tool integration.
  • Contribute design and code reviews to maintain secure, maintainable, and reusable components.
  • Recommend whether to build, reuse, or discontinue approaches based on evidence from working implementations.
  • Build evaluations and quality gates that assess output quality, groundedness, hallucination rate, reliability, security, usefulness, latency, and cost.
  • Analyze production transcripts and user feedback to improve workflows iteratively.
  • Version, test, deploy, monitor, and maintain prompts, context, and components using software engineering discipline.
  • Design for reliability through provider or model fallback, graceful degradation, timeouts, and retries, while managing inference cost and latency.
  • Implement access controls, data-handling practices, traceability, and guardrails aligned with internal and customer requirements; release changes through established change-management and security-review processes.
  • Pair with team members and customer engineers to understand their work, identify valuable AI use cases, and build solutions collaboratively.
  • Help define appropriate uses and limits for AI, explaining technical constraints in actionable terms for non-specialists.
  • Teach by building, writing clear examples, documenting components, and helping engineers create and extend AI workflows.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service