AI Engineer - Remote (3x/wk) TS/SCI w/Poly, Agentic AI

Shield Consulting Solutions, Inc.; Maryland; Hybrid; USD 130,000 - 185,000; Full time

Benefits offered by this job

Health insurance

Paid time off 25 days

11 holidays

401(k) employer match

Job summary

Shield Consulting Solutions, Inc. is seeking an AI Engineer to join our team and advance AI-enabled capabilities within the RAD architecture. You will collaborate with system and software engineers to design, prototype, and integrate LLM-driven features that automate reporting workflows and support intelligence operations.

The role emphasizes applying existing language models to real mission tasks, building multi-agent pipelines, prompt engineering, and ensuring robust testing before deployment.

Qualifications

• Strong Python development skills with production-quality code.
• Experience building apps on top of existing LLMs via APIs.
• Experience designing multi-agent or multi-step AI workflows.
• Strong prompt engineering and evaluating LLM outputs.
• Experience integrating AI into RESTful APIs and microservices.
• Experience with the AWS cloud platform.

Responsibilities

• Lead design and development of AI-driven solutions with multi-agent workflows.
• Integrate foundation models into the RAD architecture via APIs and orchestration frameworks.
• Design prompts and agent instructions to automate tasks and decompose workflows.
• Develop robust testing and evaluation strategies for AI outputs.
• Collaborate with system engineers, software developers, and domain experts.
• Stay current with evolving LLM and agentic AI technologies.

Skills

Python

LLMs

Multi-agent workflows

Prompt engineering

RESTful APIs

AWS

Tools

LangChain

LlamaIndex

Custom frameworks

Job description

Shield Consulting Solutions, Inc. is seeking an AI Engineer to join our team and advance AI-enabled capabilities within the RAD architecture. You will collaborate with system and software engineers to design, prototype, and integrate LLM-driven features that automate reporting workflows and support intelligence operations.

The role emphasizes applying existing language models to real mission tasks, building multi-agent pipelines, prompt engineering, and ensuring robust testing before deployment.