AI/ML Engineer - Agentic

AI/ML Engineer - Agentic

  

This role has been designed as ‘Hybrid’ with an expectation that you will work on average 2 days per week from an HPE office.

Job Description:

   

Job Definition:

The AI/ML Engineer – Agentic is a senior individual contributor responsible for designing, building, and operating a production-grade agentic orchestration platform, including multi-agent workflows and MCP server–based tool infrastructure. The role focuses on enterprise-scale LLM integration, shared retrieval and memory services, and high‑performance backend systems that power agent execution. This position owns reliability, observability, and cloud-native operations for non-deterministic agentic systems in production

Management Level Definition:

Contributions include applying developed subject matter expertise to solve common and sometimes complex technical problems and recommending alternatives where necessary. Might act as project lead and provide assistance to lower level professionals. Exercises independent judgment and consults with others to determine best method for accomplishing work and achieving objectives.

Responsibilities:

• Design, build, and own a production-grade agentic orchestration platform, implementing scalable multi-agent workflows using frameworks such as LangGraph or equivalent.
• Architect, develop, and operate the MCP server infrastructure, including inter-agent communication, tool/server registries, domain isolation, versioning, and lifecycle management.
• Integrate and operate LLM services at enterprise scale, supporting streaming, structured outputs, tool/function calling, and robust error handling across agent workflows.
• Build and maintain retrieval and memory services for agentic systems, including RAG pipelines, OpenSearch-backed vector stores, hybrid search, and relevance optimization.
• Develop and operate high-performance backend services (FastAPI, gRPC, async systems, messaging) that power orchestration, tool execution, and agent runtime behavior.
• Own observability and reliability for non-deterministic systems, delivering end-to-end tracing, monitoring, and cost/performance visibility for agent executions.
• Manage cloud-native infrastructure and deployment, including Kubernetes workloads, containerized services, CI/CD pipelines, and resource optimization (CPU/memory, autoscaling).

Education and Experience Required:

• Bachelor’s degree in computer science, engineering, information systems, or closely related quantitative discipline. Master’s desirable.
• Typically, 4-7 years’ experience.

Knowledge and Skills:

• Core Agentic/Orchestration:
  • Production experience with agentic frameworks: LangGraph (preferred), Claude Agent SDK, or equivalent (not just prototypes)
  • Deep understanding of multi-agent architectures: supervisor/worker patterns, hierarchical agent graphs, ReAct loops, ReWoo
  • Hands-on with inter-agent communication protocols: MCP (Model Context Protocol), A2A, tool registry / server registry
• LLM & ML Engineering:
  • LLM API integration at scale: structured outputs, streaming, function/tool calling, error handling
  • RAG pipeline design and optimization: chunking strategies, re-ranking, hybrid search - Know what knobs to turn for what issues
  • Vector store experience: OpenSearch or equivalent
  • Applied ML intuition: fine-tuning concepts, prompt engineering, evaluations, Qlora, PEFT
• Infrastructure & Pro