Artificial Intelligence Engineer

Resource Management Concepts, Inc.•Charleston, SC

5d•Onsite

About The Position

Resource Management Concepts, Inc. (RMC) is seeking an AI Engineer to design and deploy secure AI systems that connect foundation models with enterprise tools, data, and services. The role involves building agent architectures, advanced retrieval capabilities, and stateful workflows that can perform complex tasks while enforcing user permissions and maintaining reliable, controlled execution. The position calls for a hands-on engineer with experience in AI orchestration and distributed systems, and a practical approach to security, observability, and human oversight. This is a full-time, on-site position at a Government facility in Charleston, SC, contingent on contract award and position availability. The role requires an active TS/SCI clearance and the ability to obtain a CI polygraph.

Requirements

Bachelor’s degree in Cybersecurity, Computer/Electrical/Electronics Engineering, or Mathematics with a computer science concentration, or equivalent.
Hands-on production experience with MCP servers and clients, LangGraph, CrewAI, and Claude Agent SDK.
Ability to design custom cognitive architectures beyond standard frameworks.
Expertise in GraphRAG, dynamic query routing, self-correcting retrieval, context compression, state serialization, and session persistence.
Proficiency in JSON Schema and Protocol Buffers.
Experience integrating IAM tokens and claims into AI tool execution to enforce zero-trust, per-user data access.
Experience building fault-tolerant distributed systems with idempotent API or tool mutations, early-exit conditions, automated budget controls, and asynchronous human-in-the-loop suspension and resumption.
At least 5 years of relevant professional experience.
Willingness to work full-time on-site at a Government facility.
Active TS/SCI clearance and ability to obtain a CI polygraph.

Nice To Haves

Master’s degree in Cybersecurity, Computer/Electrical/Electronics Engineering, or Mathematics with a computer science concentration, or equivalent.
Experience with agent trajectory evaluation, step-level tracing using OpenTelemetry, LangSmith, or Arize Phoenix, and automated red-teaming for prompt injection and privilege escalation.
Experience deploying AI in secure, regulated, or mission-critical environments requiring auditability and data lineage.
Proficiency in Python and TypeScript or Go for building high-throughput, low-latency MCP servers and custom orchestration runtimes.

Responsibilities

Architect modular, interoperable agent ecosystems using the Model Context Protocol (MCP) to standardize connections between foundation models, external tools, and enterprise data services.
Design complex stateful workflows using production orchestration frameworks such as LangGraph, CrewAI, and Claude Agent SDK.
Engineer advanced retrieval systems, including Graph-based RAG, Agentic Routing, and Corrective RAG (CRAG).
Design memory architectures that optimize context-window utilization and manage state reliably across long-lived, multi-turn agent sessions.
Establish strict permission boundaries around autonomous tool calling.
Map JSON Schema and Protocol Buffers serialization schemas to enterprise ACLs and RBAC/ABAC policies so agents access only data and actions authorized for the invoking user.
Build resilient execution harnesses to prevent runaway agent loops and cascading failures.
Implement idempotent tool retries, token and cost budgets, deterministic early-exit conditions, and Human-in-the-Loop approval gates for high-consequence actions.