Backend Engineer - API

xAI xAI · AI Frontier · London, United Kingdom · Engineering

Backend Engineer responsible for building and owning the xAI API that serves models to developers worldwide. This includes end-to-end system ownership for high-throughput, low-latency, and highly available inference, covering model serving infrastructure, request routing, SDK development, rate limiting, observability, and scaling. Requires expertise in Rust or C++, distributed systems, and observability, with preferred experience in LLM inference engines, serving frameworks, and agent orchestration.

What you'd actually do

  1. Build the xAI API that serves our models to developers worldwide
  2. Own the end-to-end system responsible for high-throughput inference, handling billions of tokens per minute with low latency and high availability, including model serving infrastructure, request routing, SDK development, rate limiting, observability, and efficient scaling

Skills

Required

  • Rust
  • C++
  • distributed systems
  • service observability
  • reliability best practices
  • PostgreSQL
  • Clickhouse
  • MongoDB
  • gRPC

Nice to have

  • LLM inference engines
  • serving frameworks
  • SGLang
  • TensorRT
  • vLLM
  • agent SDKs
  • agent orchestration frameworks
  • Docker
  • Kubernetes
  • containerized applications

What the JD emphasized

  • Expert knowledge of either Rust or C++
  • Experience in designing, implementing, and maintaining reliable and horizontally scalable distributed systems
  • Knowledge of service observability and reliability best practices
  • Experience with LLM inference engines and serving frameworks (e.g., SGLang, TensorRT, vLLM)
  • Experience designing or building with agent SDKs and agent orchestration frameworks

Other signals

  • high-throughput inference
  • low latency
  • high availability
  • model serving infrastructure
  • request routing
  • SDK development
  • rate limiting
  • observability
  • efficient scaling
  • LLM inference engines
  • serving frameworks
  • agent SDKs
  • agent orchestration frameworks