Irfan Shaik

About

AI/software engineer with experience at Visa building a real-time transaction fraud/risk scoring microservice in the card authorization path (Python, Kafka, Kubernetes on AWS) with strict 120–150ms latency constraints and reason-code outputs for downstream decisioning. Owns ML backend end-to-end (data/feature engineering, model training, deployment) and has demonstrated production reliability work including latency spike mitigation, SLO-based observability, drift monitoring, and safe fallbacks to rule-based decisions.

Experience

Education

Key Strengths

• Built and operated real-time fraud risk scoring service in card authorization flow with 120–150ms latency budget
• Debugged and reduced latency spikes under traffic surges via feature pipeline optimization, Kafka tuning, and Kubernetes autoscaling
• End-to-end ownership of ML backend: data prep/feature engineering, model training, and deployment as scalable Dockerized inference service
• Designed reliable multi-step scoring workflow with clear failure handling, retries/alerts, and safe fallback to rule-based decisions to avoid blocking authorizations
• Strong production engineering practices: typed/Pydantic-validated interfaces, CI testing, structured logging, metrics, and SLO-based on-call alerting
• Improved PostgreSQL analytics performance using indexed relational design plus nightly-refreshed materialized views (20s+ to <2s query time)