Agentic AI & MCP Specialist

Job Description

Responsibilities
The Agentic AI & MCP Specialist will architect, develop, and operationalize next‑generation agentic systems powered by advanced LLMs and Model Context Protocol (MCP) frameworks. This role focuses on building intelligent, multi‑step, tool‑using agents that can autonomously reason, plan, and execute complex workflows across a cloud‑based analytics ecosystem. The specialist will design and implement agent orchestration frameworks, integrate model‑driven decision logic, and build robust, production‑grade agent capabilities that safely leverage emerging AI techniques.
This position requires a deeply skilled software developer who combines strong engineering fundamentals with hands‑on experience creating agentic systems, working with MCP‑based integrations, designing LLM‑driven tools, and building secure, scalable AI applications. The role provides technical leadership, explores cutting‑edge agentic patterns, drives proof‑of‑concept innovation, and partners with engineering and product teams to translate experimental architectures into real‑world impact.

Qualifications
Minimum of 8 years with BS/BA; Minimum of 6 years with MS/MA; Minimum of 3 years with PhD

Mandatory Requirements:

• Strong software engineering background with deep experience building production‑grade applications and services.
• Expertise developing agentic AI systems, including planning, tool‑use, multi‑step reasoning, workflow execution, or autonomous decisioning logic.
• Hands‑on experience designing and implementing MCP‑based integrations, tool interfaces, or model‑driven service frameworks.
• Ability to translate ambiguous business or mission requirements into scalable AI-driven solutions, balancing technical feasibility with real-world impact.
• Proficiency with LLM development practices including fine‑tuning, RAG integration, prompt engineering, and interaction models for agent workflows.
• Strong Python development skills and familiarity with distributed compute environments, APIs, microservices, and cloud‑native architectures.
• Experience integrating agents or LLM‑driven components into cloud platforms (Azure, AWS, GCP) or large‑scale data ecosystems.
• Understanding of LLMOps/MLOps principles including versioning, testing, deployment automation, monitoring, and governance for agentic systems.
• Demonstrated ability to lead solution design, mentor developers, and communicate complex AI architectures to technical and non‑technical stakeholders.
• Version control and modern CI/CD practices (e.g., Git/GitHub), including automated testing, deployment pipelines, & release management for production systems.
• US Citizen with the ability to obtain/maintain a Public Trust clearance.

Preferred Requirements:
• Experience building multi‑agent systems, agent swarms, or coordinated reasoning frameworks.
• Familiarity with advanced tool‑calling strategies, including dynamic tool selection, function‑call planning, or graph‑structured task planners.
• Experience with structured LLM evaluation methods, agent benchmarking, or test harnesses for autonomous systems.
• Knowledge of performance optimization techniques for LLMs and agents, including caching, model distillation, model routing, or accelerated inference.
• Background integrating agentic components with large‑scale data or analytics platforms (e.g., Databricks, Snowflake, Spark).
• Hands‑on experience developing innovative POCs or experimental agentic architectures in fast‑paced R&D environments.
• Familiarity with emerging agentic frameworks such as Strands Agents, LangGraph, CrewAI, etc.
• Exposure to safety‑oriented design patterns for autonomous systems, including guardrails, validation layers, or constrained‑action frameworks.
• Experience designing and building secure, compliance-aware systems that handle sensitive data in accordance with HIPAA and federal security standards, including implementation of encryption, access controls, auditability, and governance for protected health information (PHI) within AI/LLM workflows.

Peraton Overview
Peraton is a next-generation national security company that drives missions of consequence spanning the globe and extending to the farthest reaches of the galaxy. As the world's leading mission capability integrator and transformative enterprise IT provider, we deliver trusted, highly differentiated solutions and technologies to protect our nation and allies. Peraton operates at the critical nexus between traditional and nontraditional threats across all domains: land, sea, space, air, and cyberspace. The company serves as a valued partner to essential government agencies and supports every branch of the U.S. armed forces. Each day, our employees do the can't be done by solving the most daunting challenges facing our customers. Visit
peraton.com
to learn how we're keeping people around the world safe and secure.

Target Salary Range
$135,000 - $216,000. This represents the typical salary range for this position. Salary is determined by various factors, including but not limited to, the scope and responsibilities of the position, the individual's experience, education, knowledge, skills, and competencies, as well as geographic location and business and contract considerations. Depending on the position, employees may be eligible for overtime, shift differential, and a discretionary bonus in addition to base pay.
EEO
EEO: Equal opportunity employer, including disability and protected veterans, or other characteristics protected by law.

The Agentic AI & MCP Specialist will architect, develop, and operationalize next‑generation agentic systems powered by advanced LLMs and Model Context Protocol (MCP) frameworks. This role focuses on building intelligent, multi‑step, tool‑using agents that can autonomously reason, plan, and execute complex workflows across a cloud‑based analytics ecosystem. The specialist will design and implement agent orchestration frameworks, integrate model‑driven decision logic, and build robust, production‑grade agent capabilities that safely leverage emerging AI techniques.
This position requires a deeply skilled software developer who combines strong engineering fundamentals with hands‑on experience creating agentic systems, working with MCP‑based integrations, designing LLM‑driven tools, and building secure, scalable AI applications. The role provides technical leadership, explores cutting‑edge agentic patterns, drives proof‑of‑concept innovation, and partners with engineering and product teams to translate experimental architectures into real‑world impact.

Requirements

Minimum of 8 years with BS/BA; Minimum of 6 years with MS/MA; Minimum of 3 years with PhD

Mandatory Requirements:

• Strong software engineering background with deep experience building production‑grade applications and services.
• Expertise developing agentic AI systems, including planning, tool‑use, multi‑step reasoning, workflow execution, or autonomous decisioning logic.
• Hands‑on experience designing and implementing MCP‑based integrations, tool interfaces, or model‑driven service frameworks.
• Ability to translate ambiguous business or mission requirements into scalable AI-driven solutions, balancing technical feasibility with real-world impact.
• Proficiency with LLM development practices including fine‑tuning, RAG integration, prompt engineering, and interaction models for agent workflows.
• Strong Python development skills and familiarity with distributed compute environments, APIs, microservices, and cloud‑native architectures.
• Experience integrating agents or LLM‑driven components into cloud platforms (Azure, AWS, GCP) or large‑scale data ecosystems.
• Understanding of LLMOps/MLOps principles including versioning, testing, deployment automation, monitoring, and governance for agentic systems.
• Demonstrated ability to lead solution design, mentor developers, and communicate complex AI architectures to technical and non‑technical stakeholders.
• Version control and modern CI/CD practices (e.g., Git/GitHub), including automated testing, deployment pipelines, & release management for production systems.
• US Citizen with the ability to obtain/maintain a Public Trust clearance.

Preferred Requirements:
• Experience building multi‑agent systems, agent swarms, or coordinated reasoning frameworks.
• Familiarity with advanced tool‑calling strategies, including dynamic tool selection, function‑call planning, or graph‑structured task planners.
• Experience with structured LLM evaluation methods, agent benchmarking, or test harnesses for autonomous systems.
• Knowledge of performance optimization techniques for LLMs and agents, including caching, model distillation, model routing, or accelerated inference.
• Background integrating agentic components with large‑scale data or analytics platforms (e.g., Databricks, Snowflake, Spark).
• Hands‑on experience developing innovative POCs or experimental agentic architectures in fast‑paced R&D environments.
• Familiarity with emerging agentic frameworks such as Strands Agents, LangGraph, CrewAI, etc.
• Exposure to safety‑oriented design patterns for autonomous systems, including guardrails, validation layers, or constrained‑action frameworks.
• Experience designing and building secure, compliance-aware systems that handle sensitive data in accordance with HIPAA and federal security standards, including implementation of encryption, access controls, auditability, and governance for protected health information (PHI) within AI/LLM workflows.