AI Integration Engineer

About the role

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.

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

• 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.
• Candidate AI Usage Policy: The use of artificial intelligence (AI) or other tools to assist with responses during interviews (whether in-person or virtual) is prohibited unless permission is explicitly provided.

Pay

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

Schedule

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.

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.