AI Engineer: Multi-Agent Systems for Government

artificial intelligence and robotics laboratory (itu air lab); Pittsburgh (Allegheny County); On-site; USD 120,000 - 170,000; Full time

Job summary

Air is seeking an experienced AI Engineer to join our Agentic AI team in Pittsburgh, focusing on scalable multi-agent systems and real-time decision workflows for government and industry.

The role emphasizes LLM integration, tool orchestration, and reliable execution across long-horizon tasks, with opportunities to shape architecture and evaluation frameworks in a fast-paced startup-like environment.

Qualifications

• U.S. Citizenship is required.
• 1+ year of production ML/LLM experience.
• BS/MS/PhD in CS/CE/Data Science or related field.
• Advanced Python programming.
• Experience with LLM algorithms/implementations.
• Hands-on AWS/cloud deployment experience.
• Willingness to learn new tech.
• Git experience.
• Able to work with minimal supervision.
• Startup experience a plus.

Responsibilities

• Designs multi-agent systems with tool use, memory, routing, and planning.
• Develops modular agent skills and tools interacting with backend systems and data processing.
• Own the technical architecture and engineering standards for agentic systems.
• Assist with automated evaluation of agents, skills, and prompts across the product lifecycle.
• Collaborate with Product and Implementation teams to apply agents to customer problems.

Skills

LLM integration

Agent SDKs

Observability & telemetry

Ambiguity handling

Startup experience

Multi-agent coordination

Coding agents

Python

AWS & cloud

Git & collaboration

US Citizenship

Travel readiness

Education

Bachelor/Master/PhD in CS/CE/Data Science

Tools

AWS

Job description

Air is seeking an experienced AI Engineer to join our Agentic AI team in Pittsburgh, focusing on scalable multi-agent systems and real-time decision workflows for government and industry.

The role emphasizes LLM integration, tool orchestration, and reliable execution across long-horizon tasks, with opportunities to shape architecture and evaluation frameworks in a fast-paced startup-like environment.