Aptive seeks an experienced, innovative, and technically skilled Agentic AI Lead to design, develop, and deploy advanced AI agent systems powered by Claude. In this role, the Agentic AI Lead will architect and build intelligent, autonomous agents that solve complex real-world problems across diverse domains to advance Aptive’s enterprise performance. This position requires deep technical expertise in prompt engineering, agentic workflows, tool integration, and responsible AI development practices.

The Agentic AI Lead will work closely with functional leaders, engineering teams, and customers to design, prototype, and deploy production-ready AI agents that leverage Claude's capabilities through the Anthropic API, Claude Code, and emerging agentic platforms. This role requires both strategic thinking and hands-on development skills to transform business requirements into robust agent architectures, while managing multiple concurrent projects in a fast-paced, innovation-driven environment. The ideal candidate brings demonstrated experience building production AI systems, preferably using large language models and agentic frameworks, and excels at balancing technical innovation with practical deployment considerations. The Agentic AI Lead consistently delivers high-quality solutions by designing effective prompt strategies, implementing robust tool-use patterns, ensuring alignment with AI safety principles, and collaborating effectively with cross-functional teams to meet evolving customer needs and technical requirements.

• 2+ years' experience designing, developing, or deploying AI/ML systems, intelligent automation, or software applications, preferably with large language models or conversational AI systems.
• Experience working with Anthropic's Claude API, OpenAI, or similar foundation model platforms is strongly preferred.
• Bachelor's degree in Computer Science, Software Engineering, Data Science, AI/ML, or a related technical discipline.
• Demonstrated ability to lead AI development initiatives and collaborate with cross-functional teams, including data scientists, software engineers, product managers, domain experts, and customers, while maintaining clear, effective written and verbal communication with technical and non-technical stakeholders.
• Proven experience in advanced prompt engineering, including chain-of-thought reasoning, few-shot learning, prompt chaining, and systematic prompt optimization techniques to achieve reliable agent behaviors.
• Strong programming proficiency in Python and experience with API integration, tool-use/function-calling patterns, error handling, and building production-grade applications that interact with LLM APIs.
• Ability to manage multiple concurrent AI development projects with competing priorities in a fast-paced, innovation-driven environment while maintaining code quality, documentation standards, and security best practices.
• Proficiency with development tools and platforms including version control (Git/GitHub), API testing tools (Postman, curl), cloud platforms (AWS, GCP, Azure), and collaboration tools used to coordinate development workflows.

• Strategic, solutions-oriented AI developer with strong attention to detail and the ability to architect and implement a wide range of agentic systems, from research assistants and coding agents to workflow automation and decision-support tools.
• Demonstrated experience designing and implementing multi-step agentic workflows, including task decomposition, dynamic planning, tool orchestration, memory management, and error recovery patterns.
• Deep familiarity with Anthropic's product ecosystem, including Claude API capabilities (streaming, tool use, extended context), Claude Code, prompt caching, batch API, and best practices for responsible AI development and deployment.
• Experience building Model Context Protocol (MCP) servers or integrating AI agents with external tools, APIs, databases, and enterprise systems to extend agent capabilities beyond text generation.
• Proven ability to implement safety measures and guardrails in AI systems, including input validation, output filtering, harmful content detection, and alignment with responsible AI principles.
• Strong analytical and problem-solving skills with experience evaluating agent performance, conducting ablation studies, analyzing failure modes, and translating findings into systematic improvements and stakeholder recommendations.
• Experience with agentic frameworks and libraries (LangChain, LlamaIndex, AutoGen, CrewAI, or similar) and understanding of when to use frameworks versus custom implementations.
• Highly skilled in designing evaluation frameworks and testing strategies for AI agents, including unit testing for prompts, integration testing for multi-step workflows, and measuring success metrics aligned with business objectives.

Aptive partners with federal agencies to achieve their missions through improved performance, streamlined operations and enhanced service delivery. Based in Alexandria, Virginia, we support more than a dozen agencies including Veterans Affairs, Transportation, Defense, Homeland Security and the National Science Foundation. ​

We specialize in applying technology, creativity and human-centered services to optimize mission delivery and improve experiences for millions of people who count on government services every day. ​

Founded: 2012
Employees: 300+ nationwide

Aptive is an equal opportunity employer. We consider all qualified applicants for employment without regard to race, color, national origin, religion, creed, sex, sexual orientation, gender identity, marital status, parental status, veteran status, age, disability, or any other protected class.

Veterans, members of the Reserve and National Guard, and transitioning active-duty service members are highly encouraged to apply.