Lead AI Engineer

Accountabilities: As a Lead AI Engineer, you will own the technical direction of AI-enabled solutions from initial discovery through deployment and continuous improvement. Your responsibilities will include: Define and lead the architecture of generative AI solutions, including multi-agent workflows, retrieval-augmented generation (RAG), and large language model (LLM) integrations. Establish engineering standards, architectural guidelines, and best practices for developing reliable, scalable AI systems. Design, develop, and deploy multi-agent orchestration solutions and custom Model Context Protocol (MCP) servers to connect AI agents securely with enterprise and mission systems. Build applications integrating commercial and government-approved LLM endpoints, including Anthropic, OpenAI, and Ask Sage. Apply advanced prompt engineering, dataset routing, and confidence-gating techniques to improve AI output quality, accuracy, and reliability. Engage directly with government stakeholders to gather requirements, assess technical feasibility, and develop rapid prototypes that demonstrate operational value. Lead full-stack application development, including front-end, back-end, API, and data-layer design, implementation, documentation, testing, and debugging. Design and implement cloud-based data environments and pipelines that support AI workflows, including document ingestion, classification, and knowledge-domain routing. Develop AI evaluation frameworks and testing environments for regression testing, citation verification, and retrieval transparency. Conduct adversarial testing and red-team exercises to identify prompt injection vulnerabilities and other potential AI failure modes before production deployment. Ensure AI solutions comply with Department of War security and regulatory requirements, including Authority to Operate (ATO) and FedRAMP standards. Lead, mentor, and support engineering teams in adopting AI tools, AI-first development methodologies, and emerging technologies. Encourage collaboration and knowledge sharing through technical initiatives, workshops, and hackathons. Incorporate field feedback and operational requirements into product roadmaps, collaborating with product leadership on release planning and prioritization. Coordinate system installations, monitor production performance, and ensure deployed AI capabilities meet technical specifications and mission requirements. Work closely with multidisciplinary teams to continuously improve the performance, security, and operational effectiveness of AI solutions. Requirements The ideal candidate combines extensive software engineering experience with hands-on expertise in generative AI, strong technical leadership, and the ability to deliver secure solutions in complex operational environments. The following qualifications are expected: Bachelor's degree in Computer Science, Software Engineering, or a related field, combined with at least 15 years of professional experience. Demonstrated experience leading engineering teams or serving as a technical lead on complex software development initiatives. Hands-on experience designing, developing, and deploying generative AI or agentic AI systems in production or operational environments. Strong understanding of multi-agent orchestration, retrieval-augmented generation (RAG), prompt engineering techniques, including few-shot prompting and chain-of-thought approaches, and LLM API integration. Proficiency in both front-end and back-end software development. Experience with Python, .NET/C#, Angular, TypeScript, Docker, AWS services, SQL Server, web and data pipelines, and Git-based CI/CD workflows. Familiarity with equivalent technologies is also accepted, including React, Java, PostgreSQL, and Azure. Experience delivering software solutions in secure and regulated environments, including ATO processes, FedRAMP compliance, and security hardening. Strong analytical, troubleshooting, and problem-solving skills, with a focus on delivering reliable, high-quality, mission-ready solutions. Excellent communication skills and the ability to explain AI capabilities, limitations, technical decisions, and trade-offs to both technical and non-technical stakeholders. Ability to collaborate effectively with government customers, engineering teams, product managers, and other multidisciplinary stakeholders. Preferred qualifications: Experience designing and developing custom Model Context Protocol (MCP) servers. Familiarity with AI-assisted software development tools such as Claude Code, Cursor, and GitHub Copilot Agents. Experience with Helm, YAML, GitLab, Qlik, or Databricks. Background in developing AI evaluation frameworks and conducting adversarial testing of LLM-based systems. Experience with data warehousing, ETL processes, and business intelligence solutions. Familiarity with integrating AI capabilities into enterprise workflow platforms, including custom Power Automate connectors. Benefits Opportunity to lead the development of advanced generative AI and agentic systems. Exposure to cutting-edge AI technologies, cloud platforms, and enterprise software architectures. Technical leadership opportunities within multidisciplinary engineering teams. Direct collaboration with government stakeholders on mission-critical projects. Opportunity to influence AI product strategy, architecture, and technical roadmaps. Professional growth through continuous learning, mentorship, and exposure to emerging AI technologies. Inclusive and equal-opportunity working environment. Opportunity to contribute to innovative solutions supporting national security and complex government operations.