Agentic AI Engineer — Multi-Agent Systems & Planning

Air; Pittsburgh (Allegheny County); On-site; USD 120,000 - 190,000; Full time

Job summary

Air is seeking an experienced AI Engineer to join our Agentic AI team in Pittsburgh, PA, focusing on scalable agentic offerings for US government applications. You will design, implement, and iterate on agentic architectures, planning, and tool use with LLMs, aiming for reliable long-horizon tasks and inter-agent coordination.

The role emphasizes building frontend-interacting agents, observability, and evaluation loops, with startup-like urgency and a strong appetite for learning new AI

Qualifications

• Bachelor's degree in CS/CE/Data Science or related field.
• 5+ years of progressive experience designing, building, and deploying production ML/LLM systems.
• Practical experience in building, developing, and productionizing ML systems.
• Advanced software skills in Python.
• Experience with common LLM algorithms and implementations.
• Hands-on experience with AWS and cloud infrastructure.
• Strong desire to learn new technologies.
• Familiarity with Git and version control.
• Ability to work collaboratively with minimal supervision.
• Desire to work in a fast-paced tech environment.

Responsibilities

• Design multi-agent systems with tool use, memory, routing, and planning.
• Develop Agent Skills and modular tools interacting with backend systems and data processing.
• 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

Python

LLMs

Machine Learning

AWS

Git

Collaboration

Education

Bachelor's degree in CS/CE/Data Science

Tools

Claude SDK

OpenAI SDK

Job description

Air is seeking an experienced AI Engineer to join our Agentic AI team in Pittsburgh, PA, focusing on scalable agentic offerings for US government applications. You will design, implement, and iterate on agentic architectures, planning, and tool use with LLMs, aiming for reliable long-horizon tasks and inter-agent coordination.

The role emphasizes building frontend-interacting agents, observability, and evaluation loops, with startup-like urgency and a strong appetite for learning new AI