AI LLMOps Engineering Technical Leader

Cisco seeks an AI LLMOps Engineering Technical Leader to operationalize agentic AI and MLOps systems on its Customer Experience (CX) platform. This role focuses on building MLOps pipelines, model serving architectures, and telemetry monitoring while managing GPU-based inference infrastructure. You will drive reliability, security, and performance for AI-driven customer-facing products.

• Drive operationalization of autonomous agent architectures into secure, scalable production environments.
• Establish robust MLOps practices, ML pipelines, and model serving architectures.
• Design and implement telemetry monitoring for token usage, compute cost, agent reasoning paths, and model performance.
• Manage containerized models on GPU clusters and resolve model inference issues.
• Guide architectural choices based on market knowledge and mentor team members.

• Bachelor's degree and 8+ years related experience, or Master's and 6+ years.
• Experience in Software Engineering and DevOps building scalable infrastructure.
• Experience operationalizing LLMs such as OpenAI, Anthropic, Llama and using LLM frameworks like LangChain or LangSmith.
• Proficiency in Python and/or Java/J2EE.
• Experience building APIs with FastAPI, Flask, Spring Boot or similar.
• Knowledge of CI/CD concepts for ML, model tracking frameworks (ClearML, MLflow, Weights & Biases), Docker, and Kubernetes.