AI Orchestration & Retrieval Architect (Remote)

Maxonic Inc.; King of Prussia (PA); On-site; USD 180,000 - 260,000; Full time

Job summary

Maxonic Inc. is seeking a Principal Engineer, AI Orchestration & Retrieval in King of Prussia, PA, with remote work flexibility. You will define how our central AI system connects LLMs to tools, data, and agents, and shape retrieval and chunking strategies.

You will lead design of MCP servers, tool surfaces, and multi-agent patterns, mentoring engineers and aligning with product teams to onboard capabilities as tools and agents within a scalable, observable platform.

Qualifications

• 12 or more years of experience in software/AI engineering.
• Hands-on experience building LLM orchestration, agents, and retrieval systems.
• Experience with LLM orchestration frameworks and agentic patterns.
• Direct experience building MCP servers and tool/function-calling integrations.
• Defensible point of view on tool quantity and API count per MCP server.
• Experience with retrieval/RAG, embeddings, vector databases, hybrid search, re-ranking.
• Experience designing abstraction layers and platform APIs.
• Strong understanding of context-window management, prompt assembly, and cost/latency optimization.
• Experience with evaluation and observability for agentic and retrieval systems.

Responsibilities

• Design the orchestration and abstraction layers of the central AI system that connect LLMs to tools, data, and sub-agents
• Build and operate MCP servers and standards for how tools are defined, exposed, and versioned
• Define tool-surface strategy: optimal number of tools & APIs per MCP server, and coherence of tool surfaces
• Establish when to use specialized sub-agents versus direct tool exposure, and design multi-agent patterns
• Design retrieval (RAG) systems: chunking strategies, embeddings, vector stores, hybrid/keyword search, re-ranking, and context assembly
• Define abstraction layers that decouple product teams from the underlying models, tools, and providers
• Build routing, context-window management, and memory strategies for agentic workflows
• Define evaluation for orchestration and retrieval quality (retrieval precision/recall, tool-selection accuracy, task success, latency, and cost)
• Establish observability and tracing across multi-step agent and tool calls
• Address safety, guardrails, authentication, and access control across tools and agents
• Partner with product teams to onboard their capabilities as tools and agents into the central AI system
• Mentor engineers and raise orchestration and retrieval maturity across teams

Skills

LLM orchestration

Agents

Retrieval systems

Context window management

Cost & latency optimization

Observability & tracing

Tool-surface design

Safety & access control

Multi-agent patterns

Tools

LangGraph

LlamaIndex

Semantic Kernel

Job description

Maxonic Inc. is seeking a Principal Engineer, AI Orchestration & Retrieval in King of Prussia, PA, with remote work flexibility. You will define how our central AI system connects LLMs to tools, data, and agents, and shape retrieval and chunking strategies.

You will lead design of MCP servers, tool surfaces, and multi-agent patterns, mentoring engineers and aligning with product teams to onboard capabilities as tools and agents within a scalable, observable platform.