AI Engineer: Multi-Agent Systems & LLM Orchestration

Air; Pittsburgh (Allegheny County); On-site; USD 130,000 - 195,000; Full time

Job summary

Air in Pittsburgh, PA is seeking an experienced AI Engineer to join the Agentic AI team and scale agentic offerings across US government workloads. The role focuses on planning, reliable execution over long-horizon tasks, tool use, memory, and inter-agent coordination with human inputs.

You will demonstrate a project built on LLMs showing your ability to orchestrate complex tasks, integrate Claude or OpenAI SDKs, and build observability and evaluation loops for agent behavior. U.S.

Qualifications

• U.S. Citizenship is required.
• Bachelor's, Master's, or Doctorate in Computer Science, Computer Engineering, Data Science, or a related field.
• Minimum 1 year of experience building and deploying ML or LLM-powered systems in production environments.
• Hands-on experience with AWS and cloud infrastructure.
• Experience designing and deploying complex agentic systems using LLMs.
• Experience with multi-agent coordination, routing, and tool orchestration.

Responsibilities

• Designs and builds multi-agent systems with tool use, memory, routing, and planning.
• Develops Agent Skills and tools as modular, composable services that interact with backend systems, models, and data processing.
• Own the technical architecture and engineering standards for agentic systems, ensuring scalability, reliability, and maintainability.
• Assist with automated evaluation of agents, skills, and prompts across the entire product lifecycle.
• Work with Product and Implementation teams to apply agents to customer problems.

Skills

Python

LLM workflows

AWS cloud

Agent frameworks

Git

Team collaboration

Education

Bachelor's/Master’s/Doctorate in CS/CE/DS

Tools

Claude Agent SDK

OpenAI Agent SDK

Job description

Air in Pittsburgh, PA is seeking an experienced AI Engineer to join the Agentic AI team and scale agentic offerings across US government workloads. The role focuses on planning, reliable execution over long-horizon tasks, tool use, memory, and inter-agent coordination with human inputs.

You will demonstrate a project built on LLMs showing your ability to orchestrate complex tasks, integrate Claude or OpenAI SDKs, and build observability and evaluation loops for agent behavior. U.S.