Software Engineer - Training/Inference (C++)

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

SpaceX was founded under the belief that a future where humanity is out exploring the stars is fundamentally more exciting than one where we are not. Today, SpaceX is actively developing the technologies to make this possible, with the ultimate goal of making life multiplanetary and expanding consciousness to the stars.
SpaceXSI is building Super Intelligence to help humanity understand the universe. Our teams are building the full Super Intelligence stack: from our Colossus supercomputers, to Grok models, to our suite of applications, including Grok Bot, Grok Build, Grok Imagine, Grok Voice, and X. We're creating a powerful flywheel where more compute trains better models, better models power more useful products, and what we learn from people using those products shapes what we build next.

About the Role:

SpaceX was founded under the belief that a future where humanity is out exploring the stars is fundamentally more exciting than one where we are not. Today, SpaceX is actively developing the technologies to make this possible, with the ultimate goal of making life multiplanetary and expanding consciousness to the stars.
SpaceXSI is building Super Intelligence to help humanity understand the universe. Our teams are building the full Super Intelligence stack: from our Colossus supercomputers, to Grok models, to our suite of applications, including Grok Bot, Grok Build, Grok Imagine, Grok Voice, and X. We're creating a powerful flywheel where more compute trains better models, better models power more useful products, and what we learn from people using those products shapes what we build next.

• We are building the high-performance inference platform that serves Grok to millions of users every day with lightning speed and perfect reliability.
• As a Member of Technical Staff - Inference, you will design and optimize large-scale model serving systems end-to-end. You will own everything from distributed infrastructure (global KV cache, continuous batching, load balancing, auto-scaling) to deep low-level optimizations (GPU kernels, quantization, speculative decoding, tail latency).
• This is a high-impact role where your work directly determines how fast and reliably users interact with Grok at massive scale

Responsibilities:

• Architect and implement scalable distributed infrastructure for model serving (load balancing, auto-scaling, batch scheduling, global KV cache).
• Optimize latency and throughput of model inference under real production workloads.
• Build reliable, high-concurrency serving systems that serve billions of users with 100% uptime, 0% error rate, and excellent tail latency.
• Benchmark, fine-tune, and accelerate inference engines (including low-level GPU kernel work and code generation).
• Develop custom tools to trace, replay, and fix issues across the full stack — from orchestration down to GPU kernels.
• Create robust CI/CD infrastructure for seamless endpoint deployment, image publishing, and inference engine updates.
• Accelerate research on scaling test-time compute, RL rollout, and model-hardware co-design for next-generation systems.

BASIC QUALIFICATIONS:

• Deep low-level systems programming (C/C++ or Rust)
• Experience with large-scale, high-concurrent production serving.
• Experience with GPU inference engines (vLLM, SGLang, Triton, TensorRT-LLM, etc.).
• Strong background in system optimizations: batching, caching, load balancing, parallelism.
• Low-level inference optimizations: GPU kernels, code generation.
• Algorithmic inference optimizations: quantization, speculative decoding, distillation, low-precision numerics.
• Experience with testing, benchmarking, and reliability of inference services.
• Experience designing and implementing CI/CD infrastructure for inference.

$180,000 - $440,000 USD

Base salary is just one part of our total rewards package at SpaceXSI , which also includes equity, comprehensive medical, vision, and dental coverage, access to a 401(k) retirement plan, short & long-term disability insurance, life insurance, and various other discounts and perks.

SpaceXSI is an equal opportunity employer. For details on data processing, view our Recruitment Privacy Notice.