Low-Level C++ Engineer | Ultra-Low Latency Market Making (HFT) - New York (Relocation Supported)

Environment: C++20/23 • Linux • Kernel-bypass Networking • FPGA • RDMA • Nanosecond Execution

Their engineers operate where nanoseconds decide P&L, measured, profiled, and deployed in live markets where performance is the edge. They’re now seeking an elite C++ Engineer to design and optimise the core of a real-time execution platform, ingesting millions of market events per second and reacting deterministically, faster than anyone else.

The Role

You’ll work directly on the systems that drive trading outcomes in production, spanning market data, execution, and capture, where jitter, contention, and worst-case behaviour matter more than averages. This is not a role for engineers who optimise for benchmarks or theory, only those who care about how systems behave under real market stress.

You’ll operate across:

• Market Data & Connectivity: handling venue-specific feeds at line rate without introducing jitter, back-pressure, or hidden latency under burst conditions
• Execution Path: controlling tail latency and ensuring deterministic behaviour under load
• Simulation Fidelity: building environments where results transfer cleanly to production
• Capture & Replay: lossless, deterministic pipelines that don’t pollute the critical path
• Systems Engineering: CPU pinning, NUMA, memory layout, and Linux/network tuning

Every optimisation has a cost. Improving one path can degrade another. The challenge is knowing what actually matters in live markets.

What You’ll Do

• Build and optimise low-level, multi-threaded C++ across market data, order entry, and execution
• Own performance end-to-end: profiling, instrumentation, debugging, and proof
• Scale systems across venues and regions without compromising determinism or correctness
• Work in tight loops with traders and quants, shipping, measuring, iterating

What We’re Looking For

• Expert C++ in performance-critical systems, including hot paths, allocation, contention, and tail latency
• Deep understanding of concurrency, CPU and memory behaviour, and low-latency design
• Strong Linux systems experience and performance tooling
• A mindset of measurement over assumption, everything is profiled, nothing is guessed

Bonus

• HFT or exchange connectivity experience, including feed handlers, gateways, and protocols
• Familiarity with FIX, OUCH, ITCH, or similar
• Experience with deterministic simulation, capture and replay, or research-to-production systems

The Environment

Flat, highly technical, and performance-driven. Engineers sit close to the problem and the outcome, with no layers and no dilution. Code that is faster in production directly impacts the business.

Why Join

• Work on systems where worst-case latency, not averages, defines success
• High ownership and direct influence over system design
• Top-of-market upside, top performers can exceed $1.5M total comp
• Relocation support to New York