AI Safety & Reasoning Engineer; Reasoning Transparency
-
IT/Tech
Job Description & How to Apply Below
The application window is expected to close on: 12/30/2026
Meet the TeamJoin Cisco’s Enterprise AI team, the core group enabling Generative AI powered experiences across Cisco. Our mission is to build secure, scalable AI platforms that empower teams to safely develop, deploy, and operationalize AI-powered solutions. We operate at the intersection of applied AI, cloud infrastructure, and security, partnering across engineering, security, compliance, and product teams to bring trusted AI to life at enterprise scale.
We are a fast-growing, highly collaborative team of platform engineers, AI engineers, and data scientists who value technical depth, ownership, and pragmatic execution. What makes this team exciting is the opportunity to define how secure Generative AI is built and governed inside a global technology leader. In this role, you will connect AI safety research with production engineering. You will develop methods and infrastructure to assess whether model behavior reflects its internal state, and help ensure deployed AI systems remain reliable, honest, and aligned as they use increasingly complex inference-time computation.
Impact
You will operationalize transparency by translating concepts from mechanistic interpretability and eliciting knowledge into scalable pipelines that run alongside model inference. You will build infrastructure to extract, map, and interpret model activations and latent representations, supporting analysis of how internal signals relate to model outputs. You will design red-teaming frameworks and automated behavioral auditing stress tests to identify misalignment, sycophancy, deceptive behavior, and coordination risks across models or agents.
You will partner with ML engineering to integrate transparency probes while managing inference latency, memory use, reliability, and operational cost. Additionally, you will track relevant AI safety research to rapidly prototype, evaluate, and deploy promising transparency methods, while defining evaluation methods to communicate evidence, limitations, and actionable findings to research, engineering, and product partners.
- Bachelors + 7 years of related experience, or Masters + 4 years of related experience, or PhD + 1 year of related experience, or equivalent related work experience
- Hands‑on experience deploying or operating machine learning models in a production or production‑like environment using Python.
- Demonstrated 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 utilize adversarial prompt engineering to probe model limits and ensure model reliability and safety.
- 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.
Why Cisco?
At Cisco, we’re revolutionizing how data and infrastructure connect and protect organizations in the AI era – and beyond. We’ve been…
(If this job is in fact in your jurisdiction, then you may be using a Proxy or VPN to access this site, and to progress further, you should change your connectivity to another mobile device or PC).
View / Apply for Jobs
Matching My Jurisdiction