Principal AI Engineer

Responsibilities

• Transform validated AI prototypes (RAG/agentic workflows) into production-grade software systems
• Own the AI API surface, including contracts, schemas, versioning, and backward compatibility
• Implement reliability patterns such as circuit breakers, rate limiting, retries, and graceful degradation
• Build end-to-end observability using structured logging, metrics, and OpenTelemetry tracing
• Design service boundaries and integration patterns for AI capabilities within a regulated environment
• Lead and mentor a team of data and software engineers, setting technical direction and conducting design reviews
• Drive operational readiness through runbooks, CI/CD for AI services, and incident retrospectives
• Partner with DevOps/SRE and Data Science teams to ensure high availability and data lineage

Requirements

• 7+ years of experience building production-grade backend systems
• Proficiency in TypeScript or Python at a production level (writing services, not just scripts)
• Proven experience with RAG and agentic workflows
• Expertise in observability tools, specifically OpenTelemetry
• Experience leading and mentoring engineering teams
• Strong SQL fluency for investigating system behavior and data issues
• Deep understanding of reliability engineering, including SLOs, SLAs, and resiliency patterns

About the Company

Alpheya is a B2B WealthTech startup based in Abu Dhabi, backed by BNY Mellon and Lunate. With $300M in funding, we are building a state-of-the-art wealth technology platform designed to empower financial institutions in the Middle East to serve affluent and UHNW investor segments.