jobctl

Software Engineer - Training/Inference (C++)

SpaceXSI - Palo Alto, CA, Seattle, WA - original posting ->
Status
Open
Remote policy
Not stated
Employment type
Not stated
Salary
Not stated
Categories
Infrastructure
Tech
cpprustsoftware
Source
xai
First observed
2026-08-18 21:02 UTC
Last seen
2026-10-13 05:08 UTC
Source claims posted
2024-10-05 00:14 UTC
Consecutive misses
0 of 3

What the posting says

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 understand the universe and help expand humanity’s knowledge and capabilities. We work across the full Super Intelligence stack: compute (Colossus supercomputers), models (Grok), and applications (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:

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.

COMPENSATION AND BENEFITS:

$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.

Quality

Completeness: 45%
Honesty: 100%

Based on 18 observation(s).

Timeline

  1. *
    #161948 2026-08-18 21:02 UTC
    Published
  2. ~
    #167675 2026-08-19 01:02 UTC
    Modified
    • source_updated_at
      2026-08-18T15:14:36-04:00->2026-08-18T18:10:46-04:00
  3. ~
    #199899 2026-08-20 01:16 UTC
    Modified
    • source_updated_at
      2026-08-18T18:10:46-04:00->2026-08-19T18:53:03-04:00
  4. ~
    #231345 2026-08-21 04:27 UTC
    Modified
    • source_updated_at
      2026-08-19T18:53:03-04:00->2026-08-20T20:36:54-04:00
  5. ~
    #259307 2026-08-21 23:53 UTC
    Modified
    • source_updated_at
      2026-08-20T20:36:54-04:00->2026-08-21T18:24:01-04:00
  6. ~
    #388615 2026-08-26 22:37 UTC
    Modified
    • source_updated_at
      2026-08-21T18:24:01-04:00->2026-08-26T17:48:54-04:00
  7. ~
    #394243 2026-08-27 06:39 UTC
    Modified
    • source_updated_at
      2026-08-26T17:48:54-04:00->2026-08-26T23:12:24-04:00
  8. ~
    #407489 2026-08-27 22:40 UTC
    Modified
    • source_updated_at
      2026-08-26T23:12:24-04:00->2026-08-27T18:09:48-04:00
  9. ~
    #557820 2026-09-03 21:32 UTC
    Modified
    • Locations
      Palo Alto, California->Palo Alto, CA
    • source_updated_at
      2026-08-27T18:09:48-04:00->2026-09-03T14:58:20-04:00
  10. ~
    #564574 2026-09-04 05:32 UTC
    Modified
    • source_updated_at
      2026-09-03T14:58:20-04:00->2026-09-04T00:53:32-04:00
  11. ~
    #646387 2026-09-08 23:51 UTC
    Modified
    • source_updated_at
      2026-09-04T00:53:32-04:00->2026-09-08T18:33:02-04:00
  12. ~
    #963302 2026-09-24 06:03 UTC
    Modified
    • source_updated_at
      2026-09-08T18:33:02-04:00->2026-09-23T23:22:06-04:00
  13. ~
    #975046 2026-09-24 18:07 UTC
    Modified
    • source_updated_at
      2026-09-23T23:22:06-04:00->2026-09-24T13:08:25-04:00
  14. ~
    #1100334 2026-09-30 22:44 UTC
    Modified
    • source_updated_at
      2026-09-24T13:08:25-04:00->2026-09-30T16:41:12-04:00
  15. ~
    #1189391 2026-10-05 18:50 UTC
    Modified
    • Locations
      Palo Alto, CA->Palo Alto, CA, Seattle, WA
    • source_updated_at
      2026-09-30T16:41:12-04:00->2026-10-05T11:32:06-04:00
  16. ~
    #1295389 2026-10-12 13:22 UTC
    Modified
    • Description
      SpaceXAI’s mission is to create AI systems that can accurately understand the universe and aid humanity in its pursuit of knowledge. Our...->SpaceX was founded under the belief that a future where humanity is out exploring the stars is fundamentally more exciting than one where...
  17. ~
    #1311462 2026-10-13 01:08 UTC
    Modified
    • Description
      SpaceX was founded under the belief that a future where humanity is out exploring the stars is fundamentally more exciting than one where...->SpaceX was founded under the belief that a future where humanity is out exploring the stars is fundamentally more exciting than one where...
    • source_updated_at
      2026-10-05T11:32:06-04:00->2026-10-12T19:35:19-04:00
  18. ~
    #1314436 2026-10-13 05:08 UTC
    Modified
    • Organisation
      SpaceXAI->SpaceXSI