AI Systems Engineer – Production ML & RAG Pipelines

Taswiq4me; Lorton (VA); Hybrid; 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, owning RAG pipelines, evaluation, and performance optimization across enterprise data. You will build scalable, observable AI services for mission-critical federal environments, with cloud-native architectures and strong security practices.

The role requires 3+ years building AI/ML production systems, experience with LLM workflows, embedding pipelines, and API design using FastAPI/Flask/Node.js.

Qualifications

• 3+ years of experience building production AI/ML systems.
• Experience building LLM systems using RAG frameworks or similar pipelines.
• Experience designing embedding pipelines and APIs using FastAPI/Flask/Node.js.
• Familiarity with AWS services and security best practices.
• Experience implementing observability and performance tuning.

Responsibilities

• Design and deliver production-grade AI systems in federal environments.
• Own RAG pipelines, evaluation, and performance optimization.
• Build scalable, observable AI services with modern infrastructure.

Skills

RAG pipelines

LLM systems

Observability

Performance tuning

Prompt engineering

API design

Distributed systems

Cloud-native

LangChain

LlamaIndex

Pinecone

Weaviate

FAISS

OpenSearch

FastAPI

Flask

Node.js

AWS Bedrock

SageMaker

EKS

S3

IAM

Lambda

CloudWatch

Datadog

OpenTelemetry

Redis

Ray Serve

Triton

Education

Bachelor's degree

Tools

LangChain

LlamaIndex

Pinecone

Weaviate

FAISS

OpenSearch

FastAPI

Flask

Node.js

AWS Bedrock

SageMaker

EKS

S3

IAM

Lambda

CloudWatch

Datadog

OpenTelemetry

Redis

vLLM

Ray Serve

Triton Inference Server

Job description

Booz Allen Hamilton is seeking an AI Engineer to design and deliver production-grade AI systems, owning RAG pipelines, evaluation, and performance optimization across enterprise data. You will build scalable, observable AI services for mission-critical federal environments, with cloud-native architectures and strong security practices.

The role requires 3+ years building AI/ML production systems, experience with LLM workflows, embedding pipelines, and API design using FastAPI/Flask/Node.js.