Backend API Engineer: Scale AI Inference (Rust/C++)

SpaceX Super Intelligence; Greater London; On-site; GBP 107,000 - 262,000; Full time

Benefits offered by this job

Equity

Healthcare

Dental coverage

Cash plan

Life insurance

Job summary

SpaceXSI is pursuing an ambitious backend infrastructure to support its Grok models and associated applications. We are looking for an experienced engineer to build and operate scalable, reliable systems in production, with a focus on Rust or C++ and a high-throughput inference stack.

You will own the API services that expose models to developers, ensuring low latency, high availability, and strong observability across distributed components. Equity and comprehensive benefits accompany the role.

Qualifications

• Expert-level knowledge of scalable distributed systems and backend infrastructure.
• Experience with Rust or C++ in production-grade services.
• Familiarity with observability, error handling, and reliability best practices.
• Hands-on experience with PostgreSQL, Clickhouse, and MongoDB.

Responsibilities

• Build the SpaceXSI API that serves models to developers worldwide.
• Own end-to-end high-throughput inference systems with low latency and high availability, including model serving, routing, SDKs, rate limiting and observability.

Skills

Rust or C++

Distributed systems design

Observability & reliability

PostgreSQL / Clickhouse / MongoDB

Tools

Docker

Kubernetes

Containerization

Job description

SpaceXSI is pursuing an ambitious backend infrastructure to support its Grok models and associated applications. We are looking for an experienced engineer to build and operate scalable, reliable systems in production, with a focus on Rust or C++ and a high-throughput inference stack.

You will own the API services that expose models to developers, ensuring low latency, high availability, and strong observability across distributed components. Equity and comprehensive benefits accompany the role.