Staff Inference Engineer - High-Performance Serving

SpaceX Super Intelligence; Seattle (WA); On-site; USD 180,000 - 440,000; Full time

Benefits offered by this job

Equity

Medical, vision, and dental coverage

401(k) retirement plan

Disability and life insurance

Job summary

SpaceXSI is building a high-performance inference platform to serve Grok to millions daily. You will design end-to-end scalable distributed infrastructure, from global KV caches to auto-scaling and batching, while optimizing GPU kernels and low-level inference components.

You will own performance, reliability, and tail latency in production workloads, building tools for traceability and rapid updates across the full stack.

Qualifications

• Deep low-level systems programming experience.
• Experience with large-scale, high-concurrency production serving.
• Background in GPU inference engines and optimizations.

Responsibilities

• Architect scalable distributed infrastructure for model serving.
• Optimize latency and throughput under production workloads.
• Build high-concurrency serving systems with very high availability.
• Benchmark and accelerate inference engines and GPU kernels.
• Develop tools to trace, replay, and fix issues across the stack.
• Create CI/CD for seamless endpoint deployment and updates.
• Advance research on scaling test-time compute and co-design.

Skills

C/C++

Rust

High-concurrency serving

GPU inference engines

Batching

Caching

Load balancing

Quantization

Code generation

Reliability testing

Tools

vLLM

SGLang

Triton

TensorRT-LLM

CUDA

Job description

SpaceXSI is building a high-performance inference platform to serve Grok to millions daily. You will design end-to-end scalable distributed infrastructure, from global KV caches to auto-scaling and batching, while optimizing GPU kernels and low-level inference components.

You will own performance, reliability, and tail latency in production workloads, building tools for traceability and rapid updates across the full stack.