Job Title: AI Engineer

Location: Pittsburgh, PA (Onsite)

About The Company

Our client transforms Defense Acquisition from an outdated manual process into a software-driven strategic advantage for the United States government. Their flagship platform supports Supply Chain, Science & Technology, Production, Sustainment, Logistics, and Modernization teams through AI-enabled applications and best-in-class data. Trusted by every branch of the U.S. military and the broader national security community, their team enables faster, more informed acquisition decisions that directly impact national defense.

They foster a fast-paced, mission-driven environment where innovation, ownership, and technical excellence are highly valued. Employees are empowered to solve complex challenges that have meaningful impact on global security and defense modernization.

Job Summary

We are seeking an AI Engineer to join its Agentic AI team in Pittsburgh, PA. This individual will play a key role in scaling and enhancing a rapidly growing AI agent platform. The ideal candidate is a hands-on builder with experience designing and deploying LLM-powered systems, agentic workflows, and production-grade AI solutions.

This role will focus on developing multi-agent systems, agent skills, memory architectures, tool orchestration frameworks, and automated evaluation capabilities that enable AI agents to solve increasingly complex government and defense challenges. The successful candidate will thrive in highly ambiguous environments, demonstrate strong engineering ownership, and have a passion for building cutting-edge AI systems.

Key Responsibilities

Design & Build Agentic Systems: Develop and deploy advanced multi-agent architectures incorporating planning, memory, tool use, routing, and autonomous execution capabilities.

Develop Agent Skills & Services: Create modular, reusable Agent Skills and tools that integrate with backend systems, AI models, APIs, and data processing pipelines.

Architect Scalable AI Solutions: Own technical architecture decisions and establish engineering standards that ensure scalability, reliability, maintainability, and long-term performance.

Implement Evaluation & Observability Frameworks: Build automated evaluation systems, telemetry pipelines, regression testing frameworks, and feedback loops to continuously improve agent performance.

Collaborate Across Functions: Partner closely with Product, Implementation, and Engineering teams to apply agentic AI solutions to customer challenges and drive product innovation.

Requirements

Education: Bachelor's, Master's, or Doctorate degree in Computer Science, Computer Engineering, Data Science, or a related technical field

Experience: Minimum 1 year of experience building and deploying machine learning or LLM-powered systems in production environments. Experience designing, developing, and productionizing machine learning solutions. Experience working in fast-paced, highly ambiguous environments. Experience integrating and working with large language models (LLMs).

Skills: Advanced Python development skills. Strong understanding of LLM capabilities, limitations, and implementation techniques. Experience with agent frameworks such as Claude Agent SDK, OpenAI Agent SDK, or similar technologies. Experience with AWS cloud infrastructure. Familiarity with Git source control. Strong problem-solving and debugging abilities. Ability to work independently while collaborating effectively across teams

Other Requirements

U.S. Citizenship required
Ability to obtain and maintain a U.S. security clearance
Ability to travel up to 25%
Strong desire to learn emerging technologies and innovate within AI systems

Preferred Qualifications

Experience designing and deploying complex agentic AI systems
Experience with multi-agent coordination, orchestration, and routing
Hands-on experience building tool-use frameworks and autonomous workflows
Experience implementing observability, evaluation, and reliability metrics for AI agents
Startup or entrepreneurial experience, particularly within zero-to-one product development

environments

Experience with Claude Code and GenAI engineering best practices
Existing U.S. security clearance
Demonstrated personal or professional AI projects showcasing advanced LLM capabilities

Benefits

Competitive Compensation

Competitive salary
Performance bonus opportunities
Equity participation opportunities

Health & Wellness

Comprehensive healthcare benefits
Medical, dental, and vision coverage

Work-Life Balance

Paid time off and company holidays
Mission-focused work environment
Opportunity to contribute directly to U.S. national security initiatives

Professional Development

Exposure to cutting-edge AI technologies and large-scale agentic systems
Opportunity to work alongside leading AI engineers and defense technology experts
Continuous learning and technical growth opportunities

Additional Perks

High-impact work supporting the U.S. defense community
Collaborative startup-style culture
Ownership and autonomy in technical decision-making
Opportunity to shape the future of AI-enabled defense acquisition