Staff Backend AI Engineer, Remote at Experian — NeverHard

Job Description Overview We are looking for a Staff Software Engineer to lead the delivery of high-throughput, large-scale transactional systems and agentic AI applications. You will serve as a technical anchor across engineering squads - setting the bar for code quality, cloud architecture, and engineering excellence while mentoring the next generation of engineers. You will report to the Sr. Principal Engineer. Responsibilities: Architect, build, and own services for large-scale transactional platforms — ensuring high availability, fault tolerance, and sub-second performance at millions of transactions per second. Lead the end-to-end design of agentic AI workflows using orchestration frameworks, such as LangGraph, AutoGen, and CrewAI. Implement these workflows using tool-calling patterns and multi-agent coordination on AWS. Write production-grade Python and Go services; establish language-specific idioms, patterns, and performance baselines adopted across engineering teams. Design and govern AWS-native infrastructure (ECS, EKS, Lambda, MSK, RDS Aurora, DynamoDB, SageMaker, or EventBridge) - ensuring solutions align with the AWS Well-Architected Framework. Establish engineering standards: code review practices, test coverage requirements, CI/CD pipelines, and observability instrumentation (distributed tracing, structured logging, alerting). Conduct and lead technical design reviews for new services, integrations, and platform changes; produce high-quality architecture decision records (ADRs) and technical specs. Resolve performance bottlenecks in distributed systems, including database query optimization, caching strategies, and async processing patterns. Guide proof-of-concept (PoC) work for new technologies and evaluate their production readiness; present recommendations to engineering leadership. Mentor and level up senior and mid-level engineers through structured code reviews, pairing sessions, and technical coaching. Contribute to on-call rotations, incident response, and post-mortem processes to guide systemic reliability improvements.