AI Engineer The Opportunity: Join a hands-on AI engineering team building and deploying LLM-powered applications. In this role, youll implement core components of AI systems, including prompting, retrieval pipelines, and API integrations, while gaining experience with the tooling and infrastructure required to run AI workloads in production. Youll work across the full AI application lifecycle from data ingestion and retrieval to prompt engineering, evaluation, deployment, and production operations building secure, mission-focused AI solutions for federal clients. You Have: 31+ years of experience in software engineering, data engineering, or applied AI/ML31Experience building applications in Python using frameworks such as FastAPI or Flask, and building and integrating applications using LLM APIs such as OpenAI, AWS Bedrock, or Azure OpenAI31Experience implementing Retrieval-Augmented Generation (RAG) pipelines, including document ingestion, chunking, embeddings, retrieval workflows, and prompt augmentation31Experience with vector databases such as FAISS, Pinecone, Weaviate, or OpenSearch Vector Search, and cloud environments, including AWS services such as S3, Lambda, EC2, IAM, and CloudWatch31Experience using Git, basic CI/CD pipelines, and containerization with Docker31Experience designing or consuming REST APIs and working with structured outputs such as JSON schemas and function or tool calling31Knowledge of prompt engineering, prompt evaluation, and common LLM failure modes, including hallucinations, prompt injection, data leakage, jailbreak attempts, and grounding techniques31Knowledge of prompt evaluation techniques and response quality testing31Ability to obtain a TS/SCI clearance 31Bachelors degree Nice If You Have: 31Experience with orchestration frameworks such as LangChain or LlamaIndex31Experience with embeddings via OpenAI, Cohere, or SentenceTransformers31Experience with monitoring and logging tools such as CloudWatch or Datadog31Experience deploying services using Docker Compose or Kubernetes31Experience with structured logging and debugging distributed API failures31Experience with AWS Secrets Manager or AWS Systems Manager Parameter Store31Experience with asynchronous Python programming or background processing31Experience with Model Context Protocol (MCP) or modern AI tool integration standards Clearance: Applicants selected will be subject to a security investigation and may need to meet eligibility requirements for access to classified information. Compensation Salary at Booz Allen is determined by various factors, including but not limited to location, the individuals particular combination of education, knowledge, skills, competencies, and experience, as well as contract-specific affordability and organizational requirements. The projected compensation range for this position is $77,600.00 to $176,000.00 (annualized USD). The estimate displayed represents the typical salary range for this position and is just one component of Booz Allens total compensation package for employees. This posting will close within 90 days from the Posting Date. Work Model Our people-first culture prioritizes the benefits of collaboration, whether it occurs in person or virtually. To support engagement and effective communication, employees working virtually are generally expected to have their cameras on during meetings. 31Remote: If this position is listed as remote, there may still be occasions when you are required to work in person at a Booz Allen or customer facility. 31Hybrid: If this position is listed as hybrid, you will be expected to work from a Booz Allen facility frequently, in alignment with leadership expectations and the needs of the role. You may also be required to work from or visit a customer facility. 31Onsite: If this position is listed as onsite, work will primarily be performed at a Booz Allen office or customer facility, where employees will collaborate directly with colleagues and customers as required by the role.