AI Integration Engineer

About the role

As an AI Engineer, you will integrate AI-enabled capabilities into existing software systems by connecting models, inference endpoints, and orchestration components to production applications. You will implement AI features using established integration and software engineering patterns, ensuring these capabilities operate reliably, securely, and efficiently within distributed systems. You’ll contribute to evaluation and monitoring approaches, refine integration workflows, and collaborate with cross-functional teams to deliver scalable AI functionality. Your work will help bring AI from concept into real-world environments through thoughtful, well-structured engineering.

Responsibilities

• Build and maintain production software systems in Python
• Integrate external services or APIs into distributed systems
• Implement inference request flows, including handling latency, token limits, and batching strategies
• Write integration tests for multi-service environments
• Integrate large language models into production services, including managing inference requests, model responses, and error-handling flows
• Design and implement HTTP API design patterns, including authentication mechanisms such as OAuth2, API keys, or JWT
• Manage containerization and CI/CD pipelines
• Collaborate with cross-functional teams to deliver scalable AI functionality

Requirements

• 3+ years of experience building and maintaining production software systems in Python
• Experience integrating external services or APIs into distributed systems
• Experience implementing inference request flows, including handling latency, token limits, and batching strategies
• Experience writing integration tests for multi-service environments
• Experience integrating large language models into production services, including managing inference requests, model responses, and error-handling flows
• Knowledge of HTTP API design patterns, including authentication mechanisms such as OAuth2, API keys, or JWT
• Knowledge of containerization and CI/CD pipelines
• Ability to travel up to 25% of the time
• TS/SCI clearance with a polygraph

Qualifications

• Bachelor’s degree in CS, Engineering, or Data Science

Skills

• Experience with message queues or event streaming, including Kafka, and patterns for idempotency and handling out-of-order or duplicate events
• Experience implementing resilience patterns such as retries with backoff, timeouts, and circuit breakers, to ensure reliable system behavior
• Experience with cloud AI platform tooling such as AWS Bedrock AgentCore, Google Gemini Enterprise Agent Platform, or Microsoft Foundry Agent Service
• Experience with Docker, Kubernetes, or Infrastructure-as-Code tooling
• Experience with multi-step agentic workflows or orchestration concepts and how they integrate into existing systems
• Experience with agent memory concepts such as session-level and persistent state, and how they relate to application logic
• Experience with orchestration frameworks for AI-enabled systems such as LangGraph, CrewAI, or AutoGen, and supporting data stores such as Redis and Postgres

Benefits

• Health, life, disability, financial, and retirement benefits
• Paid leave
• Professional development
• Tuition assistance
• Work-life programs
• Dependent care
• Recognition awards program

Pay

The projected compensation range for this position is $112,800.00 to $257,000.00 (annualized USD).

Schedule

Full-time and part-time employees working at least 20 hours a week on a regular basis are eligible to participate in Booz Allen’s benefit programs. Individuals that do not meet the threshold are only eligible for select offerings, not inclusive of health benefits.

Individuals selected for this position will be subject to a security investigation and may need to meet eligibility requirements for access to classified information; TS/SCI clearance with a polygraph is required.