Systems Engineer (Contract, LATAM)

About Nexus

Nexus is building the AI gateway for modern companies — one platform that gives teams access to the world's leading AI models while keeping costs predictable, security under control, and workflows connected.

Companies can use Nexus to access models like GPT, Claude, Gemini, and many others through a unified platform. Our infrastructure helps organizations choose the right model for each task, manage usage and budgets, enforce access policies, and integrate AI into the tools their teams already use.

Headquartered in San Francisco with a growing presence in Latam, Nexus is a cross-continental team building the infrastructure that makes AI more accessible, efficient, and manageable at scale.

We're investing deeply in the Latin American engineering ecosystem and looking for exceptional talent to help us build the next generation of AI infrastructure.

Nexus is backed by leading investors, including Pantera, Lightspeed, Dragonfly, Faction, Blockchain Builders Fund, Alliance, and SVA.

Location: Remote
Type: Contract
Duration: 12 months with potential for extension

The Role

We’re expanding our systems engineering team in Latin America to build the high-performance core of Nexus’s AI gateway.

This is not a typical backend role. You’ll work on the performance-critical path that every AI request travels through: request routing, streaming, rate limiting, and the data plane that connects enterprises to multiple AI models in real time. Every millisecond and every allocation counts.

We’re looking for Systems Engineers who enjoy working close to the metal, optimizing for throughput and latency, and building software that stays fast and correct under heavy load.

You’ll collaborate closely with engineering and product teams in San Francisco while contributing remotely from Latin America.

What You’ll Do

• Design and implement high-performance components for Nexus’s AI gateway data plane in Rust, C++, or Go.

• Build low-latency systems for request routing, load balancing, and failover across AI providers.

• Develop efficient streaming pipelines for real-time model responses, including token streaming and long-lived connections.

• Build high-throughput rate limiting, quota enforcement, and usage metering that adds minimal latency to each request.

• Optimize concurrency, memory usage, networking, and I/O paths for throughput and tail latency.

• Investigate and resolve performance bottlenecks using profiling, tracing, and benchmarking.

• Help define standards for performance, reliability, and correctness across the platform.

• Collaborate with backend, infrastructure, and product teams to ship new features and improve existing systems.
  

What We’re Looking For

• Strong experience with Rust, C++, Go, or other systems programming languages.

• Solid computer science fundamentals, including data structures, algorithms, and operating systems.

• Understanding of high-performance or distributed systems, such as proxies, networking stacks, databases, runtimes, or OS-level concurrency.

• Strong grasp of concurrency, async I/O, and networking protocols (TCP, HTTP/2, gRPC, WebSockets).

• Practical experience profiling CPU, memory, and synchronization overhead.

• Comfort working on systems where performance, correctness, and resilience are critical.

• Strong problem-solving skills and the ability to work through complex technical challenges.

• Excellent communication skills in Business English, both spoken and written.
  

  Levels We're Hiring

  • Junior 1–3 years - Solid foundations, eagerness to grow, guided ownership

  • Principal 8+ years - System design leadership, cross-team impact, mentorship, leading 5 Jr engineers in parallel and teams of at least 10 engineers

Bonus Points For

• • Experience building proxies, API gateways, load balancers, or networking infrastructure (Envoy, NGINX, Pingora, or similar).

  • Experience with LLM inference, AI infrastructure, or streaming AI APIs.

  • Familiarity with lock-free concurrency, zero-copy techniques, or cache-aware design.

  • Experience building low-latency systems such as trading engines, databases, or real-time platforms.

  • Open-source contributions to systems-level projects.

  • Competitive programming or hackathon background (ICPC or similar).
    

Why Join Us

• Build the future of enterprise AI: Engineer the performance-critical core that connects companies to the world’s leading AI models.

• Solve meaningful technical challenges: Work on low-latency routing, real-time streaming, and high-throughput systems where your optimizations are felt on every request.

• Work with emerging AI technologies: Build at the intersection of systems engineering and AI infrastructure.

• Have a direct impact: Shape the architecture of a growing platform where engineering decisions matter.

• Collaborate with an international team: Work alongside talented engineers and product builders across San Francisco and Latin America.

• Grow in a fast-moving environment: Grow into system ownership or drive architecture as a Principal.