Sr. Software Engineer, Training/Inference (C++)

xAI

  • Palo Alto, CA
  • Senior level
  • 5+ yrs experience
  • Backend Engineering
  • Visa: not specified
  • $200k–$375k

The role in 30 seconds

At xAI, we are building the full Super Intelligence stack to help humanity understand the universe. Our teams are 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 looking for a Sr. Software Engineer, Training/Inference (C++) to design and optimize large-scale model serving systems end-to-end.

Is this role a fit for you?

The backgrounds this role is most likely to hire from, as RoleStack reads the posting.

Strong match

  • B2B infrastructure / API / developer tools
  • Software, SaaS & AI Platform
  • Internal tooling / back-office systems
  • Enterprise-scale
  • Growth-stage

Workable stretch

  • B2B enterprise platform / workflow software
  • Marketplace / multi-sided platform
  • Startup / greenfield

Harder transition

  • B2C consumer-facing application
  • Embedded systems / hardware-adjacent
  • Regulated environment

Industry: Software, SaaS & AI Platform. See your personal match score

What they're really screening for

Must-haves

  • PLUS Bachelor’s degree in computer science, computer engineering, or science discipline
  • CORE 5+ years of experience with low-level system programming experience in C/C++ or Rust
  • CORE Experience building and operating high-concurrency serving systems with excellent tail latency and high reliability at the scale required to serve millions of users
  • CORE Experience with large-scale, high-concurrent production serving
  • CORE Experience with GPU inference engines
  • CORE Strong background in system optimizations: batching, caching, load balancing, parallelism
  • CORE Low-level inference optimizations: GPU kernels, code generation
  • CORE Algorithmic inference optimizations: quantization, speculative decoding, distillation, low-precision numerics
  • PLUS Experience with testing, benchmarking, and reliability of inference services
  • PLUS Experience designing and implementing CI/CD infrastructure for inference

Résumé keywords for this role

Terms the posting stresses. Include the ones you can honestly back up.

Tools & technologies

  • C++
  • Rust
  • GPU
  • vLLM
  • SGLang
  • Triton
  • TensorRT-LLM
  • CI/CD
  • KV cache
  • Grok
  • Colossus
  • X

Concepts & phrases

  • Sr. Software Engineer, Training/Inference (C++)
  • low-level system programming
  • large-scale model serving systems
  • distributed infrastructure
  • global KV cache
  • continuous batching
  • load balancing
  • auto-scaling
  • deep low-level optimizations
  • GPU kernels
  • quantization
  • speculative decoding
  • tail latency
  • high-concurrency serving systems
  • production workloads

Words that count as the same thing: "Grok" ≈ large language model, AI model · "Super Intelligence" ≈ advanced AI, general AI · "Colossus" ≈ supercomputer, compute infrastructure · "tail latency" ≈ worst-case latency, p99 latency · "GPU kernels" ≈ CUDA code, GPU programming

Check my résumé against these keywords

Hiring at xAI

Open senior roles RoleStack tracks right now, posted in the last 30 days.

More open roles at xAI

Full job description from xAI

From xAI's posting. View the original

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.

Show full description Show less

SR. SOFTWARE ENGINEER, TRAINING/INFERENCE (C++)

At SpaceXSI we are building the high-performance inference platform that serves Grok to millions of users every day. As a Software Engineer, Training/Inference (C++), 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, including GPU kernels, quantization, speculative decoding, and 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 and operate high-concurrency serving systems with excellent tail latency and high reliability at the scale required to serve millions of users

• 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:

• Bachelor’s degree in computer science, computer engineering, or science discipline

• 5+ years of experience with low-level system programming experience in C/C++ or Rust

PREFERRED SKILLS AND EXPERIENCE:

• Experience with large-scale, high-concurrent production serving

• Experience with GPU inference engines (e.g., vLLM, SGLang, Triton, TensorRT-LLM)

• 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:

$200,000 - $375,000 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.

FAQ

How much does a Sr. Software Engineer, Training/Inference (C++) at xAI make?

The posted pay for this role is $200k–$375k a year.

How much experience do you need?

The posting asks for 5+ years in low-level system programming. It is a senior-level role.

Does xAI sponsor visas for this role?

The posting does not say whether visa sponsorship is available. Ask the recruiter before you apply.

What tools and technologies does the posting mention?

C++, Rust, GPU, vLLM, SGLang, Triton, TensorRT-LLM, CI/CD, KV cache, Grok, Colossus, X.