About the Role

Abnormal Security is seeking a Staff Backend Software Engineer to join our Detection Team. The Detection Division is at the forefront of developing cutting-edge technology to identify and thwart sophisticated email and cloud-based attacks that were previously undetectable, contributing to a safer digital world. As a Staff Software Backend Engineer focusing on the Detection's Serving Platform, you will be instrumental in scaling and optimizing our high-throughput, low-latency scoring infrastructure to ensure a fast, responsive, stable, and reliable experience for our customers .

The ideal candidate will possess:

• A proven track record of scaling high-throughput, low-latency model scoring infrastructure
• Experience in maintaining 99.99% uptime for services handling 50k+ QPS
• A first-principles approach to architecting scalable, customer-centric solutions
• A passion for solving complex, real-world problems with pragmatic solutions
• Strong ownership mentality and impact-driven outlook on efforts and growth
• Ability to iterate rapidly and autonomously on novel challenges
• Experience with performance engineering - in identifying and resolving bottlenecks in systems and improving the performance in an iterative way

Key Responsibilities

• Lead the architecture, design, and implementation of highly scalable backend services and infrastructure supporting our world-class Detection Engine
• Spearhead critical projects to meet ambitious goals, such as scaling components of Detection's Scoring Pipeline by 10x while maintaining or improving performance
• Collaborate closely with ML Engineering teams to gather requirements, provide technical leadership, and drive execution of infrastructure improvements
• Mentor and coach junior engineers through 1-on-1s, pair programming, and high-quality code and design reviews
• Continuously optimize system performance, reliability, and efficiency to meet growing demand and evolving threat landscape

Requirements

• 8+ years of professional experience as a hands-on engineer building and scaling data-intensive products
• Extensive experience with real-time, online, high-throughput & low-latency distributed systems
• Proven ability to maintain 99.99% uptime for services handling 50k+ QPS
• Strong track record of cross-functional collaboration and driving complex projects to completion
• Demonstrated leadership in setting and maintaining high standards for project execution and code quality
• Experience in fast-paced or start-up like environment
• Experience with cloud-native architectures and microservices
• Experience with event-driven architecture such as Kafka, Pub/Sub, etc.

Preferred Qualifications

• Familiarity with ML systems/products and distributed system technologies (e.g., Python, Golang, Kafka, Redis, Docker, Kubernetes, feature serving platforms, ML training and serving infrastructures)
• Hands-on experience optimizing high-throughput online systems
• MS or PhD in Computer Science, Electrical Engineering, or a related field
• Familiarity with the cybersecurity industry or fraud detection and its unique challenges

#LI-ML1