Agentic AI Engineer
bah · Alexandria
Job description
About the role
Booz Allen is looking for an Agentic AI Engineer to build autonomous, goal-oriented AI systems, helping shift its AI strategy from passive LLM chatbots to proactive, multi-agent orchestrations. The role uses agent orchestration frameworks, RAG, knowledge graphs and fine-tuned small language models for edge deployment.
Key responsibilities
- Design and implement agent architectures that reason, plan and act using LangChain, LangGraph and AutoGen.
- Develop and deploy multi-agent systems using Model Context Protocol (MCP) and Agent-to-Agent (A2A) protocols.
- Build RAG pipelines that integrate unstructured data with Knowledge Graphs to improve reasoning accuracy and context retention.
- Fine-tune SLMs for specific domains and optimize them for edge devices (ONNX, GGML, Ollama).
- Build evaluation frameworks for agent reliability, safety and performance, including ReAct loops and human-in-the-loop testing.
Required profile
- 2+ years of software development experience.
- 2+ years as an ML engineer building production-grade ML solutions with Docker or Kubernetes, including GenAI, LLMs, DL, RL, AI agents and agentic workflows.
- 2+ years with LangChain, LangGraph, AutoGen, PydanticAI, CrewAI or LlamaIndex.
- 2+ years in cloud environments (AWS and Azure), designing scalable service-based applications.
- Experience with MCP, A2A, RAG architecture and KG (Neo4j or NebulaGraph).
- Experience fine-tuning LLMs or SLMs with Hugging Face, PEFT or LoRA, and building observation layers (Grafana, Langfuse, LangSmith, Phoenix).
- Knowledge of modern software design patterns, including microservices and edge computing.
- Ability to adapt to rapid change and navigate ambiguity.
- TS/SCI clearance with a polygraph; applicants are subject to a security investigation.
- Bachelor's degree; Master's in CS or AI preferred, doctorate in CS or Statistics a plus.
Required skills
- LangChain, LangGraph, AutoGen, PydanticAI, CrewAI, LlamaIndex
- MCP, A2A, RAG, Knowledge Graphs (Neo4j, NebulaGraph)
- Hugging Face, PEFT, LoRA, ONNX, GGML, Ollama
- Nice to have: TensorFlow, PyTorch, llama.cpp, vLLM, production and edge deployments, coding agents such as Cursor or Windsurf
What we offer
- Health, life, disability, financial and retirement benefits, paid leave and professional development.
- Tuition assistance, work-life programs and dependent care.
- A recognition awards program for exceptional performance.
- Projected annual salary range of $77,600 to $176,000.
Questions fréquentes
Why are you reporting this job?
Explore further
Salaries, guides and searches in the United States.
Salary: Forward Deployed Engineer Based on 57 job offers in the United StatesSalaries by job title
- Delivery Specialist 330
- Line Cook 264
- Restaurant Host 251
- Dishwasher 241
- Shift Supervisor 226
- Parts Specialist 208
- Retail Service Specialist 176
- Server - Red Robin 140
Apply in 30 seconds
Enter your email to apply. An account will be created automatically.
By continuing, you accept our terms of use.
Already have an account? Login
A question about this job?
Ask it here: you will get the full job summary by e-mail, right away.
Published 4 days ago
Expires 1 month from now
11 views · 0 interested
Boost your chances
Upload your CV — we will match you with relevant openings.
Analyzing your CV...
bah
Alexandria