Design, develop, and maintain scalable software solutions supporting advanced Agentic AI capabilities
Architect and implement autonomous agent systems leveraging agentic workflows, reasoning engines, and multi-agent collaboration
Integrate AI agents with enterprise applications and distributed systems using APIs, standard protocols, and modern software architectures
Manage the complete software development lifecycle from concept and design through deployment and sustainment
Develop clean, maintainable, testable, and efficient code following modern software engineering best practices
Build and maintain microservices and RESTful APIs supporting scalable and resilient applications
Collaborate closely with engineers, architects, product managers, and mission stakeholders to rapidly deliver new capabilities
Participate in Agile/Scrum activities including sprint planning, stand-ups, technical reviews, and retrospectives
Develop and execute unit, integration, and system tests to ensure software quality and reliability
Troubleshoot, optimize, and enhance system performance across cloud and on-premise environments
Support continuous improvement efforts by evaluating emerging AI frameworks, tools, and engineering approaches
Requirements
Core Software Engineering Experience
Bachelor’s degree in Computer Science or related technical field
5+ years of professional software engineering experience using object-oriented programming languages, with significant experience in Python
Strong understanding of the full Software Development Lifecycle (SDLC), including requirements analysis, design, development, testing, deployment, and maintenance
Proficiency with git, and experience with a modern source control platform (GitLab, GitHub, Bitbucket, or similar), including branching strategies, code review, and CI/CD pipelines
Experience with issue tracking and documentation tools like Jira and Confluence (or equivalents)
Experience developing microservices and RESTful APIs
Experience working in Agile/Scrum development environments
Hands-on experience building with LLMs or agents in any context, including production systems, prototypes, or substantial personal projects
Hands-on experience with any agent framework (Microsoft Agent Framework, LangGraph, CrewAI, AutoGen, Pydantic AI, etc.).
Familiarity with agent communication and tooling protocols (MCP, A2A), or experience implementing tool-use/function-calling in an LLM-based system
RAG architectures, vector databases, or agent memory systems
Prompt engineering, evaluation frameworks (Langfuse, MLflow, DSPy), or experience tuning LLM systems for reliability
Ability to collaborate effectively across cross-functional engineering teams
Strong communication and problem-solving skills in fast-paced technical environments
Active TS/SCI U.S. Government Security Clearance
Willingness to be submitted for and ability to obtain a Counter Intelligence (CI) Polygraph