Agentic AI Cloud Development Engineer

About the role

Hewlett Packard Enterprise is hiring an Agentic AI Cloud Development Engineer in San Juan, Puerto Rico. The role is hybrid, with about two days per week spent in an HPE office. It builds and operationalizes the core agentic workflows behind Marvis, a next-generation AI assistant for network operations, combining data science, generative AI and production engineering.

Key responsibilities

• Design, implement and iterate agentic workflows using LangGraph.
• Develop and maintain MCP (Model Context Protocol) servers and skills: define tool schemas, implement domain tools, write skill playbooks and manage server lifecycle.
• Build applications in streaming or batch mode over Kafka and Spark.
• Integrate and optimize LLM capabilities at production scale, including structured outputs, streaming, function/tool calling, prompt engineering and error handling.
• Work with network engineers and product managers to turn troubleshooting playbooks into skills, tools and data pipelines.
• Develop data analysis and transformation logic in sandboxed environments, including multi-tool orchestration, aggregation and visualization.
• Deploy containerized services in Kubernetes and contribute to CI/CD pipelines, image management and health probes.
• Own observability: tracing, logging, cost tracking and performance monitoring.

Required profile

• Bachelor's or Master's degree in computer science.
• Typically 2-4 years of experience building production ML/AI systems, with at least a year of hands-on generative AI and LLM work.
• Subject-matter expertise in agentic AI and applied GenAI, able to lead projects and mentor colleagues.

Required skills

• Data engineering: production Python, FastAPI or equivalent, REST/GraphQL APIs.
• Big data: Apache Spark and Kafka (at least 2 years).
• Agentic frameworks: LangGraph strongly preferred, plus LangChain, Claude Agent SDK or equivalent.
• MCP or equivalent tool-serving protocols.
• Kubernetes, CI/CD (Jenkins, GitHub Actions, ArgoCD), Docker and container registries.
• Observability tools such as LangFuse or Prometheus.

Preferred: networking domain knowledge, AWS Bedrock or OpenSearch Serverless, and strong communication skills. Benefits include health and wellbeing support, professional development programs and an inclusive workplace.