Wade Spires

Staff engineer at Snap. I build low-latency C++ systems — messaging infrastructure, electronic trading, and LLM inference routing.

About

I write C++ for systems where latency and correctness both matter. At Snap I architected the cross-platform notification infrastructure shared by the Snapchat iOS and Android apps. Before that I built direct market-access trading infrastructure at Clover Light Capital, and low-latency trading systems at Automated Trading Desk and Citi.

The through-line is concurrent state made simple enough to reason about: single-threaded cores behind async façades, shared-nothing designs, no locks on the hot path. Lately that has meant the same problems one layer up — Ranvier, my current project, routes LLM inference requests to the backend that already holds the relevant KV cache.

Projects

Ranvier

2025C++20, Seastar

An open-source LLM inference router that cuts time-to-first-token by 33–44% by sending each request to the backend GPU already holding the relevant KV cache, measured on 8× A100s across Llama-3.1 8B, 13B, and 70B. An adaptive radix tree over token prefixes gives O(L) lookups independent of key count, and sub-50µs routing decisions. Built shared-nothing and thread-per-core on Seastar — no locks on the hot path, string_view parsing over a single network buffer copy — with circuit-breaking health checks, gossip-based clustering, and Kubernetes-native deployment.

  • 33–44%faster TTFT
  • <50µsrouting decision
  • 8× A100measured on

ranvier.systems

Gym Log+

2013 – presentSwift, SwiftUI

A strength training app for iOS, developed and shipped solo to the App Store: roughly 450,000 downloads to date. Rebuilt from the ground up in 2026.

gymlogplus.com

Experience

  1. – Present

    Staff Software Engineer Snap Inc.

    Primary C++ engineer on Snapchat's cross-platform notification infrastructure, shared between Android and iOS.

    Owned its concurrency model, persistence, and delivery-state handling.

    Technical lead on Streak Restore with Snapchat+, and lead of 5–10 engineers across backend, iOS, and Android on messaging features including Chat Reply and Chat Mentions.

  2. –

    Software Engineer Clover Light Capital

    Built proprietary futures trading infrastructure in modern C++ for CME, CFE, and Eurex. Replaced a vendor Eurex implementation with direct EOBI market data and ETI order entry, cutting median per-message latency by 55 microseconds and eliminating the licensing cost, and wrote the direct handlers for CME MDP 3.0, CFE PITCH, and CFE BOE.

  3. –

    Assistant Vice President Automated Trading Desk / Citi

    Developed, deployed, and operated low-latency trading systems in C++, Python, Perl, and Bash alongside teams across EMEA, Japan, and Australia. Extended the C++ market data readers with full order book depth and auction-phase indicative pricing, and migrated SBI Japannext to an ITCH-based feed, retiring Reuters Data Feed Direct for roughly $50K a year in data center savings.

Education

  • M.S. Computer Science University of Central Florida

  • B.S. Computer Science, B.S. Mathematics University of Tennessee

Elsewhere