Key Papers

Paxos is the foundational consensus algorithm that enables distributed systems to agree on values despite failures — the theoretical bedrock behind Google Chubby, Apache ZooKeeper, and every modern consensus protocol.

Spanner is Google's globally distributed database that provides externally consistent reads and writes — the first system to achieve global ACID transactions at scale using TrueTime and Paxos.

Since local LLM inference on resource-constrained edge devices imposes a severe performance bottleneck, this paper proposes distributed prompt caching...

Modern machine learning models are deployed in diverse, non-stationary environments where they must continually adapt to new tasks and evolving knowle...

This paper argues that reliable end-to-end graph data analytics cannot be achieved by retrieval- or code-generation-centric LLM agents alone. Although...

Engineer-friendly summary of “Attention Is All You Need” (Vaswani et al.). Learn self-attention, multi-head Q/K/V, and why Transformers beat RNN/LSTM.

Google's Distributed Storage System for Structured Data.

Amazon's distributed key-value storage system designed for high availability and eventual consistency.

Google's scalable distributed file system designed for large distributed data-intensive applications.

LinkedIn's distributed streaming platform designed for high-throughput, low-latency data streaming.

Google's simplified data processing on large clusters.

Raft protocol explained for interviews: leader election + log replication. RequestVote/AppendEntries, Raft vs Paxos, etcd/Consul use. Read now.