Staff Systems Engineer – Low Latency & Networking

United StatesRemotelead

Systems EngineerInfrastructure & Cloud

0 views0 saves0 applied

Apply Now

Quick Summary

Overview

Jito Labs is architecting the future of high-performance distributed systems on Solana. We’re the team behind Jito-Solana, the leading MEV Solana client, and the Jito Block Engine,

Technical Tools

Systems EngineerInfrastructure & Cloud

Jito Labs is architecting the future of high-performance distributed systems on Solana. We’re the team behind Jito-Solana, the leading MEV Solana client, and the Jito Block Engine, which has generated roughly 4.5 million SOL for validators and stakers over the past year.

Our latest product, BAM, reimagines Solana market structure and the transaction supply chain with a heavy emphasis on performance, reliability, and transaction privacy. We are building systems that operate at the edge of what modern hardware and networks can sustain.

We're looking for a senior engineer who is comfortable working across application code, operating systems, hardware behavior, and network protocols — someone who enjoys debugging the kinds of problems where the root cause might live anywhere in the stack.

About the Position:

We build latency-sensitive infrastructure where microseconds matter and root causes are rarely obvious. This role is for someone who can move comfortably between application code, kernel internals, hardware behavior, and network protocols — debugging a TCP retransmission anomaly one day and reasoning about memory contention the next.

You should be as comfortable reading kernel source and packet captures as you are writing production Rust. Much of the work involves ambiguous, cross-layer problems where existing tools and playbooks are insufficient and new ones must be created.

This is a senior role for someone who has previously been the person others escalate to when nobody else can find the root cause.

You'll work across:

Debug and optimize network performance end-to-end: NIC tuning, congestion control, packet pacing, queueing disciplines

Analyze traffic using tcpdump, Wireshark, and custom tooling; reason about protocol behavior under load

Work with protocols beyond TCP/UDP when required (e.g., ICMP, IGMP, multicast)

Experience with high-performance I/O and kernel-bypass techniques such as DPDK, XDP, io_uring, or similar

Read and reason about Linux kernel source when debugging requires it

Understand networking stack internals (socket buffers, congestion control, netfilter, scheduling interactions)

Build bespoke tooling when existing observability is insufficient

Work fluently with kernel interfaces used by performance-sensitive systems

Use hardware performance counters, perf, eBPF, and flamegraphs to locate real bottlenecks

Reason about practical CPU behavior: cacheline contention, branch misprediction, NUMA effects, memory ordering

Understand IRQ affinity, scheduling behavior, paging, and TLB effects under real workloads

Willing to read assembly when the situation calls for it

Strong low-level systems programming background

We work primarily in Rust, but strong experience in C or C++ is equally relevant

Solid understanding of algorithms, data structures, and writing correct concurrent code

Contribute to infrastructure, tooling, and occasionally upstream projects

10+ years of experience in systems programming, networking, or performance-critical infrastructure

Deep Linux expertise, including kernel behavior, networking internals, and performance tuning

Proficiency with packet analysis and network debugging tools

Experience with performance profiling and tracing (perf, eBPF, flamegraphs, etc.)

Strong programming fundamentals; depth matters more than language

Track record of diagnosing complex issues spanning application, OS, and hardware layers

Clear, direct communication

Experience in domains where latency and performance are first-order constraints (e.g., HFT, real-time systems, low-latency networking, kernel-adjacent infrastructure, high-performance distributed systems)

Custom memory allocators or deep memory subsystem optimization

Virtualization internals and passthrough networking (SR-IOV, vDPA, etc.)

Kernel-adjacent work (eBPF programs, driver debugging, custom modules)

Solana or blockchain infrastructure experience