AI Safety & Reasoning Engineer (Reasoning Transparency)

Cisco•Research Triangle Park, NC
•$139,300 - $203,600

About The Position

Join Cisco’s Enterprise AI team, which enables Generative AI-powered experiences across Cisco by building secure, scalable AI platforms. This role connects AI safety research with production engineering, developing methods and infrastructure to assess whether model behavior reflects its internal state and helping ensure deployed AI systems remain reliable, honest, and aligned as they use increasingly complex inference-time computation. The engineer will operationalize transparency by translating concepts from mechanistic interpretability and eliciting knowledge into scalable pipelines that run alongside model inference. The role includes building infrastructure to extract, map, and interpret model activations and latent representations, and designing methods to analyze how internal signals relate to model outputs. It also involves creating red-teaming frameworks and automated behavioral auditing stress tests, integrating transparency probes with ML engineering while managing inference latency, memory use, reliability, and operational cost, and tracking and evaluating emerging AI safety research. Findings should communicate evidence, limitations, and actionable conclusions to research, engineering, and product partners.

Requirements

  • Bachelor’s degree plus 7 years of related experience, or master’s degree plus 4 years, or PhD plus 1 year, or equivalent related work experience.
  • Hands-on experience deploying or operating machine learning models in a production or production-like environment using Python.
  • Ability to conduct rigorous empirical work and communicate technical results, assumptions, and limitations to cross-functional collaborators.
  • Practical understanding of transformer-based language models, inference-time computation, and alignment approaches such as RLHF or RLAIF.
  • Proficiency in building evaluation frameworks that use adversarial prompt engineering to probe model limits and ensure model reliability and safety.

Nice To Haves

  • High proficiency in Python frameworks, including experience building performant code for distributed training or high-throughput inference environments.
  • Hands-on experience probing, mapping, or analyzing model activations, circuits, representations, or other internal states.
  • Experience deploying and operating ML pipelines with container orchestration such as Kubernetes, CI/CD tools, and model tracking tools.
  • Experience applying information security principles or structured threat modeling to AI systems, model infrastructure, or sensitive data.
  • Familiarity with methods for eliciting model knowledge or beliefs and evaluating cases where stated outputs may diverge from internal signals.

Responsibilities

  • Translate concepts from mechanistic interpretability and eliciting knowledge into scalable pipelines that run alongside model inference.
  • Build infrastructure to extract, map, and interpret model activations and latent representations.
  • Analyze how model internal signals relate to model outputs.
  • Design red-teaming frameworks and automated behavioral auditing stress tests to identify misalignment, sycophancy, deceptive behavior, and coordination risks across models or agents.
  • Partner with ML engineering to integrate transparency probes while managing inference latency, memory use, reliability, and operational cost.
  • Track relevant AI safety research and rapidly prototype, evaluate, and deploy promising transparency methods.
  • Define evaluation methods and communicate evidence, limitations, and actionable findings to research, engineering, and product partners.

Benefits

  • Medical, dental, and vision insurance
  • 401(k) plan with Cisco matching contribution
  • Paid parental leave
  • Short- and long-term disability coverage
  • Basic life insurance
  • Cisco restricted stock unit grants may be available, subject to eligibility and continued employment
  • Paid holidays and a floating holiday for non-exempt employees
  • Employee birthday day off
  • Paid year-end holiday shutdown
  • Paid personal wellness days
  • Paid vacation or flexible vacation time off, depending on employee classification
  • Paid sick time
  • Additional paid time away may be requested for critical or emergency family issues
  • Optional paid volunteer days
  • Annual bonuses for eligible non-sales roles
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service