Data Scientist - Agentic AI

About the role

The Data Scientist – Agentic AI will design, implement, and operationalize the core agentic workflows that power Marvis, HPE’s next‑generation AI assistant for network operations. This hybrid role requires working on‑site two days per week in the San Juan office.

Key responsibilities

• Design and iterate agentic workflows using LangGraph, including ReACT loops, dynamic tool selection, multi‑step reasoning and self‑correction.
• Develop and maintain Model Context Protocol (MCP) servers, define tool schemas, write skill playbooks and manage versioned deployments.
• Integrate LLM capabilities at production scale, handling structured outputs, streaming, function calling, prompt engineering and error handling.
• Build retrieval‑augmented generation (RAG) pipelines, vector‑store search, hybrid retrieval and long‑term agent memory.
• Define evaluation frameworks for non‑deterministic systems, create metrics, run A/B tests and drive continuous quality improvement.

Required profile

• Bachelor’s, Master’s or PhD in Computer Science, Data Science, Mathematics, Statistics or a related quantitative field.
• 4‑7 years of experience building production ML/AI systems, with at least one year focused on generative AI and LLM‑based applications.
• Proven ability to work independently, lead projects and mentor colleagues in agentic AI and applied GenAI.

Required skills

• LangGraph (preferred), LangChain, Claude Agent SDK or equivalent agentic orchestration frameworks.
• Model Context Protocol (MCP) design and implementation.
• Python development in production codebases.
• Kubernetes deployment, CI/CD pipelines (Jenkins, GitHub Actions, ArgoCD), Docker container management.
• FastAPI, REST/GraphQL API design.
• Observability tools such as LangFuse, Prometheus.
• RAG pipeline design, OpenSearch or equivalent vector stores.

What we offer

• Comprehensive health, wellbeing and financial benefits.
• Personal and professional development programs.
• Inclusive workplace culture that supports flexibility and growth.