Agentic AI and Data Engineer

Booz Allen Hamilton•Honolulu, HI

11h•$99,000 - $225,000•Onsite

About The Position

Booz Allen is hiring an experienced engineer to design, develop, and deliver production-grade agentic AI systems that demonstrate the practical value of generative AI, large language models, and autonomous workflows. The role combines technical expertise and product skills to build AI applications using prompting, retrieval-augmented generation (RAG), agentic orchestration, evaluation pipelines, and human-in-the-loop systems. The engineer will architect reusable AI application patterns; integrate cloud-hosted, local, and hybrid model providers; and apply modern GenAI capabilities such as structured prompting, tool use, workflow orchestration, and multimodal reasoning. Solutions should be deployable across cloud platforms and portable, self-contained builds, with attention to latency, cost, observability, and safety. The role also involves prototyping, eval-driven development, and continuous experimentation. The engineer will help direct mission-critical agentic systems by selecting suitable prompting strategies, RAG architectures, workflows, and models. They will collaborate with AI and ML engineers, data engineers, data scientists, solutions architects, product owners, and clients to deliver solutions, identify high-value opportunities, communicate technical approaches, and support adoption. The position is located in Honolulu, Hawaii, with an additional location at Camp H.M. Smith, Hawaii. Remote work is listed as unavailable. Applicants must be able to obtain a Secret clearance and may be subject to a security investigation and eligibility requirements for classified information.

Requirements

At least 2 years of software engineering experience.
At least 2 years of professional experience in AI- or ML-focused roles.
Experience with an object-oriented programming language such as Python and applying it to AI/ML solution development.
Experience designing and implementing production-grade generative or agentic AI applications.
Experience with AI orchestration frameworks such as LangChain, agent workflows, tool integration, and multi-provider model integration.
Experience with RAG architectures, evaluation methodologies, experimentation workflows, and asynchronous or event-driven programming patterns.
Knowledge of AI data processing techniques, including text, audio, and multimodal data.
Ability to obtain a Secret clearance.
Bachelor’s degree in a computer science or engineering field.

Nice To Haves

Experience with agent frameworks, interoperability standards, and multi-agent patterns such as MCP, A2A, or LangGraph.
Experience with model fine-tuning, prompt tuning, domain adaptation, or reinforcement learning from human or AI feedback.
Experience designing AI evaluation suites or safety testing frameworks, and integrating AI systems with external tools, APIs, or enterprise systems through tool-calling or computer-use patterns.
Experience delivering AI solutions in client-facing engagements.
Experience with modern front-end libraries and component-based UI frameworks, including React, and with build pipelines, automated testing, and code quality tooling.
Experience with in-browser or edge AI execution, performance optimization, and modern build and packaging approaches for portable or offline-capable applications.
Experience with developer productivity tools such as Cursor and Windsurf.
Secret clearance.
Master’s degree in computer science, AI, or a related field.
AWS Machine Learning, Data Engineer, or Solutions Architect certification.

Responsibilities

Design adaptable agentic AI architectures supporting multiple model providers, tool ecosystems, modalities, and deployment modes.
Build reusable components for prompting, retrieval, orchestration, tool execution, memory management, and evaluation.
Integrate LLMs, embeddings, RAG pipelines, structured outputs, and long-context or memory mechanisms into production-ready systems.
Apply advanced prompting techniques, orchestration frameworks, and agentic architectures to enable goal-directed autonomy with guardrails, observability, and human oversight.
Design and implement offline and online evaluation frameworks to measure correctness, robustness, safety, and business impact.
Optimize models and workflows for cost, latency, reliability, and scalability through benchmarking and experimentation.
Develop pipelines to ingest, clean, chunk, embed, index, and continuously refresh structured and unstructured data for RAG and memory systems.
Combine text, audio, vision, and other modalities in unified workflows for document understanding, transcription, summarization, and cross-modal reasoning.
Use vector databases, hybrid search, reranking, and retrieval optimization to improve grounding and reduce hallucinations.
Incorporate guardrails, safety filters, access controls, and monitoring for responsible and secure deployment.
Deploy AI services securely and at scale on AWS or equivalent cloud platforms.
Use containers such as Docker or Kubernetes, or serverless approaches, for deployment.
Apply CI/CD and eval-driven development practices, including automated testing of prompts and workflows, versioning prompts and agents, and safely rolling out model updates.
Use asynchronous programming and event-driven patterns for scalable, long-running, or multi-agent workflows.
Use modern build and packaging workflows to deliver optimized, portable application artifacts.
Use AI assistance tools to accelerate development, debugging, and system design while maintaining engineering rigor and code quality.
Collaborate with clients to identify high-value AI opportunities and define solution requirements.
Present AI capabilities and technical solutions to technical and non-technical stakeholders.
Lead workshops and prototyping sessions to accelerate adoption.
Provide guidance on responsible AI practices, ethics, and compliance.