AI Engineer The Opportunity: As an AI engineer, you'll design and deliver production-grade AI systems. You'll own RAG pipelines, evaluation systems, and performance optimization leveraging modern AI infrastructure and tooling to build scalable, observable, and efficient services. You'll work across the full AI application lifecycle from enterprise data ingestion and retrieval to prompt engineering, evaluation, deployment, observability, and production operations building secure, scalable AI solutions for mission-critical federal environments. You Have: • 3+ years of experience building production systems, including AI/ML applications • Experience building LLM systems using RAG frameworks such as LangChain and LlamaIndex, or custom pipelines and vector stores with Pinecone, Weaviate, FAISS, or OpenSearch Vector Search • Experience designing embedding pipelines, including document ingestion, chunking strategies, indexing, metadata filtering, retrieval optimization, and hybrid search, and designing APIs and services using FastAPI, Flask, or Node.js • Experience with cloud-native architectures, including AWS services such as Bedrock, SageMaker, EKS or ECS, S3, IAM, Lambda, CloudWatch, and Secrets Manager, and agent frameworks and orchestration patterns such as LangGraph, tool calling, and function calling APIs • Experience implementing observability, including logging and tracing with OpenTelemetry, Datadog, or CloudWatch, and metrics pipelines tracking latency, throughput, token usage, cache hit rate, and error rates • Experience optimizing performance using caching layers such as Redis, parallelization or async workflows, and chunking and retrieval tuning, and designing automated evaluation pipelines using benchmark datasets, LLM-as-a-judge techniques, regression testing, and human evaluation workflows • Experience supporting production AI services, including deployment, monitoring, incident response, debugging, and performance tuning, and managing prompt templates, prompt versioning, model configurations, and structured outputs across development and production environments • Knowledge of AI security concepts, including prompt injection, jailbreak resistance, data leakage prevention, guardrails, secure prompt design, and responsible AI practices • Ability to obtain a TS/SCI clearance • Bachelor's degree Nice If You Have: • Experience supporting DoD clients or other federal mission environments • Experience with high-performance inference systems such as vLLM, Ray Serve, or Triton Inference Server • Experience with semantic caching and embedding reuse strategies • Experience with guardrail frameworks such as Rebuff, Guardrails.ai, or custom filtering systems • Experience integrating AI applications with enterprise data platforms and knowledge repositories such as Databricks, Snowflake, OpenSearch, PostgreSQL, SharePoint, Confluence, or S3-based document stores • Experience deploying AI workloads into AWS GovCloud, IL4 or IL5 environments, or other secure cloud environments • Experience with event-driven architectures and messaging technologies such as Amazon SQS, Kafka, RabbitMQ, or Amazon EventBridge • Experience with Model Context Protocol (MCP) or modern AI agent interoperability 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 individual's 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 $99,000.00 to $225,000.00 (annualized USD). The estimate displayed represents the typical salary range for this position and is just one component of Booz Allen's 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. • Remote: 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. • Hybrid: 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. • Onsite: 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.