Remote AI Engineer – Production LLM/RAG Systems

Aimlroles; Washington; On-site; USD 99,000 - 225,000; Full time

Job summary

Booz Allen Hamilton is seeking an AI engineer to design and deliver production-grade AI systems for mission-critical federal environments. You’ll own RAG pipelines, evaluation systems, and performance optimization leveraging modern AI infrastructure and tooling to build scalable, observable services.

You will work across the full AI application lifecycle from data ingestion to deployment, observability, and secure operations, requiring strong experience with LLMs, embedding pipelines, and

Qualifications

• 3+ years of experience building production AI/ML systems.
• Experience building LLM systems using RAG frameworks or custom pipelines with vector stores (e.g., Pinecone, Weaviate, FAISS, OpenSearch).
• Experience designing embedding pipelines including document ingestion, chunking, indexing, and retrieval optimization.
• Experience with cloud-native architectures (AWS Bedrock, SageMaker, EKS/ECS, S3, IAM, Lambda, CloudWatch, Secrets Manager).
• Experience implementing observability with logging/tracing (OpenTelemetry, Datadog, CloudWatch).
• Experience optimizing performance via caching, parallelization, and automated evaluation pipelines.
• Experience supporting production AI services including deployment, monitoring, and incident response.
• Knowledge of AI security concepts and responsible AI practices.
• Ability to obtain TS/SCI clearance.
• Bachelor's degree

Responsibilities

• (Not explicitly listed in HTML)

Skills

RAG frameworks

LangChain

LlamaIndex

Embedding pipelines

FastAPI/Flask/Node.js

AWS cloud services

Observability

Performance optimization

Prompt management

Education

Bachelor's degree

Tools

LangGraph

OpenTelemetry

Datadog

CloudWatch

Job description

Booz Allen Hamilton is seeking an AI engineer to design and deliver production-grade AI systems for mission-critical federal environments. You’ll own RAG pipelines, evaluation systems, and performance optimization leveraging modern AI infrastructure and tooling to build scalable, observable services.

You will work across the full AI application lifecycle from data ingestion to deployment, observability, and secure operations, requiring strong experience with LLMs, embedding pipelines, and