Principal Applied AI Engineer

Abrigo is seeking a Principal Applied AI Engineer to shape and deliver production AI capabilities across its engineering organization. The role focuses on reusable agent systems and frameworks, safe and reliable AI practices, and cross-team technical leadership to improve developer productivity and operational effectiveness.

Responsibilities:

• Lead architecture and delivery for applied AI initiatives across Platform Engineering, Cloud Operations, and product teams
• Build reusable agent frameworks, tool interfaces, skills, and reference implementations that teams can adopt
• Design reliable workflows with explicit state, recovery, bounded autonomy, and human approval suited to the risk
• Set production practices for evaluation, observability, security, reliability, cost, versioning, and controlled rollout
• Embed least privilege, permission-aware retrieval, tenant isolation, auditability, and safe tool execution into shared patterns
• Evaluate models, frameworks, and build-versus-buy options using quality, security, maintainability, latency, and cost evidence
• Influence technical direction across teams through design reviews, clear decisions, mentorship, and hands-on delivery
• Occasional travel required for team events to support engagement, relationship-building, and key decision-making

Requirements:

• Principal-level experience leading architecture and delivery of complex software, platform, or infrastructure capabilities used across teams
• 8+ years of experience in software, platform, or infrastructure engineering, including substantial technical leadership and production applied AI delivery
• Production experience with LLM workflows or agentic automation, including structured outputs, tool calling, retrieval, context management, and orchestration; sound judgment to use simpler automation when it fits
• Strong Python and backend engineering skills, plus experience building APIs and integrations with developer platforms, repositories, CI/CD, and observability systems
• Experience making AI systems dependable: evaluations and regression testing, workflow monitoring, retries and recovery, version control, rollout and rollback, and operational ownership
• Practical knowledge of AI security risks and controls, including prompt injection, data exposure, permissions, secrets, and traceable actions
• Working knowledge of AWS services such as IAM, Lambda, S3, or Bedrock, and ability to turn ambiguous needs into clear technical direction and cross-team adoption
• Experience in platform engineering, DevOps, cloud operations, or distributed systems
• experience with Terraform or other infrastructure-as-code tools, container platforms, GitHub Actions, or automation in regulated or security-sensitive environments