Autonomous AI Engineer: Multi-Agent Systems & Edge AI

Booz Allen Hamilton; McLean (VA); On-site; USD 99,000 - 225,000; Full time

Job summary

Booz Allen Hamilton is seeking a highly skilled Agentic AI Engineer in McLean, VA to shift our AI strategy toward proactive multi-agent orchestration. You will leverage LangChain, LangGraph, and AutoGen with MCP/A2A protocols, and tune SLMs for edge deployment to enable robust RAG-enabled reasoning.

You should have 5+ years in ML/DS/software, 3+ years in GenAI/LLMs, and a BS in CS/AI. The role involves production-ready agent architectures and evaluation frameworks for reliability and safety.

Qualifications

• 5+ years of experience in machine learning, data science, or software development.

Responsibilities

• Design and implement intelligent agent architectures that can reason, plan, and take actions using LangChain, LangGraph, and AutoGen.
• Develop and deploy multi-agent systems using Model Context Protocol (MCP) and Agent-to-Agent (A2A) protocols to facilitate communication, tool usage, and collaborative task solving.
• Build advanced RAG pipelines integrating unstructured data with Knowledge Graphs (KG) to enhance reasoning accuracy and context retention.
• Fine-tune SLMs for specific domains and optimize them for edge device performance, including ONNX, GGML, or Ollama.
• Develop evaluation frameworks to test agent reliability, safety, and performance, moving from prototype to production, including ReAct loops and human-in-the-loop.

Skills

Agentic AI

GenAI

LLMs

LangChain

LangGraph

AutoGen

MCP

A2A

RAG

Knowledge Graphs

Fine-tuning

Edge Deployment

ONNX

GGML

Ollama

ReAct loops

Edge Computing

Hugging Face

PEFT

LoRA

Education

Bachelor’s degree in CS or AI

Tools

LangChain

LangGraph

AutoGen

LlamaIndex

MCP

A2A

Neo4j

NebulaGraph

Hugging Face

PEFT

LoRA

ONNX

GGML

Ollama

Job description

Booz Allen Hamilton is seeking a highly skilled Agentic AI Engineer in McLean, VA to shift our AI strategy toward proactive multi-agent orchestration. You will leverage LangChain, LangGraph, and AutoGen with MCP/A2A protocols, and tune SLMs for edge deployment to enable robust RAG-enabled reasoning.

You should have 5+ years in ML/DS/software, 3+ years in GenAI/LLMs, and a BS in CS/AI. The role involves production-ready agent architectures and evaluation frameworks for reliability and safety.