Develop and deploy enterprise-scale agentic AI systems, including Multi-Agent and Agent-to-Agent (A2A) workflows, leveraging common industry standards, such as the Model Context Protocol (MCP), to create interoperable and scalable AI agents.
Implement robust MCP Tools and Resources to securely expose data and functionality, enabling LLMs to interact with internal systems and APIs in a standardized way.
Contribute to the architecture and implementation of a centralized 'AI Gateway' to ensure platform independence, Large Language Model (LLM) agnostism, and provide a unified interface for leveraging various LLMs.
Implement and manage robust observability pipelines to track trace-level data, monitor model latency, and optimize the cost and performance of Generative AI systems in production.
Collaborate closely with principal engineers, data scientists, and systems architects to translate strategic designs into hardened, production-grade solutions.
Implement and maintain robust AI guardrails to filter inputs and outputs, preventing data leakage (both into unsecure systems and future LLMs), prompt injection, and other adversarial attacks.
Apply and promote software engineering best practices, including robust version control, comprehensive automated testing, and mature CI/CD processes for AI systems.
Stay current with industry trends in agentic AI, operational AI, and MLOps to continuously evolve the team's capabilities and technical implementation.

Requirements

A Bachelor's degree in Computer Science, Engineering, or a related quantitative field with 12+ years of professional experience, or a Master's degree with 10+ years of relevant experience.
Demonstrated programming proficiency in Python and hands-on experience with major ML libraries and frameworks (e.g., TensorFlow, PyTorch, Scikit-learn).
Hands-on experience implementing solutions using the Model Context Protocol (MCP) to build standardized tools and data sources for LLM applications.
Experience with software engineering best practices and tools, including version control, automated testing, and CI/CD pipelines.
Solid understanding of the full machine learning lifecycle, from data preparation and model training to deployment and monitoring.
A strong understanding of agentic AI patterns, multi-agent systems, and LLM-based workflows.
An understanding of cybersecurity principles as they apply to AI systems, including threat modeling and vulnerability assessment.
Must be a U.S. Citizen and have the ability to obtain and maintain a U.S. security clearance.

Benefits

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

PythonTensorFlowPyTorchScikit-learnModel Context Protocol (MCP)CI/CDautomated testingversion controlmachine learning lifecycleGenerative AI

collaborationcommunicationproblem-solvingstrategic design translationadaptabilityleadership