Description

Define reliability architecture standards and resilience strategies for AI workloads across advertising platforms.

This role is on-site.

Responsibilities

• Establish latency SLOs and reliability targets for AI-dependent services.
• Design and implement circuit breaker, retry, fallback, and graceful degradation strategies.
• Lead multi-provider failover strategies across Azure, OpenAI, Bedrock, and future model providers.
• Drive resilience testing, load validation, and post-incident analysis for AI-related outages.

Required Skills

• 8+ years of backend software engineering experience building distributed systems at scale.
• Strong proficiency in Python for backend engineering.
• Microservices architecture design with strong reliability and runtime resilience patterns.
• Cloud experience with AWS and Azure for production AI workloads.
• Production reliability fundamentals including retry semantics, caching, and SLO ownership.
• Experience with OpenAI and Amazon Bedrock integrations.

Preferred Skills

• Experience designing multi-provider failover strategies.
• Background in high-throughput, low-latency service architectures.

Key Skills

Education

Any Graduate