Senior Distributed Systems Engineer, Cache

What you'll do

• Design, build, and operate the high-performance cache and proxy data plane at Cloudflare's edge.
• Contribute to Pingora to improve asynchronous I/O, connection handling, memory efficiency, and tail latency.
• Improve cache correctness and performance through object placement, retention, admission, and eviction policies.
• Build globally distributed purge systems and Tiered Cache routing to reduce origin load and increase hit rates.
• Deliver shared platform capabilities and customer-facing APIs for cache keys, TTLs, and response handling.
• Own features end-to-end by writing technical designs, implementing services, and managing staged rollouts.
• Participate in on-call rotations, lead incident responses, and perform post-mortems to improve system reliability.
• Mitigate risk by analyzing failure modes and using traffic cohorts and guardrails for high-impact changes.

What we're looking for

• Minimum 4 years of professional experience designing, building, and operating production software systems.
• Proficiency in a systems or backend language such as Rust, Go, C, or C++.
• Strong understanding of HTTP semantics and transport protocols including TCP, TLS, and QUIC.
• Experience designing and implementing secure, resilient, high-performance distributed systems.
• Experience with Linux systems, networking, concurrency, and performance analysis.
• Track record of production ownership including monitoring, debugging, on-call, and incident response.
• Experience using metrics, logs, traces, profiling, and experiments to validate improvements.
• Strong written and verbal communication skills for technical designs and cross-team collaboration.
• Willingness to use AI-assisted engineering tools while ensuring quality and security.
• Professional experience with Rust or high-performance asynchronous systems (preferred).
• Experience with caches, HTTP proxies, CDNs, distributed storage, or latency-sensitive data-plane services (preferred).
• Experience analyzing memory use, disk I/O, resource contention, and tail latency in production (preferred).
• Experience building APIs or distributed control planes using event streaming, relational databases, or analytical data systems (preferred).
• Familiarity with Kubernetes, Kafka, PostgreSQL, ClickHouse, or similar infrastructure (preferred).
• Experience contributing to open-source software or leading multi-team engineering programs (preferred).
• Authorization to receive software or technology controlled under U.S. export control laws.