Application Software Engineer, Inference

SpaceX

Quick summary

Work type: On-site
Location: Palo Alto, CA
Salary: $135,000–$160,000 / yr
Posted: 1 day ago
Nearby: 99+ roles within 25 mi

Market check

Salary context

Competitive pay

How this pay compares to similar roles

Similar $162k

This role $148k

$116k most similar roles pay here $207k

This role pays less than 55% of similar roles. Most pay $131,097–$193,000 — the shaded band above. At the midpoint, this role pays about $148k versus about $162k for comparable roles.

Based on 240 similar postings.

Employer

About SpaceX

SpaceX designs, manufactures, and launches advanced rockets and spacecraft with the mission of enabling humans to become a multi-planetary species. It operates the Falcon 9, Falcon Heavy, and Starship launch vehicles, as well as the Starlink satellite internet constellation.

SpaceX currently has 644 open roles on FindRole.

Listed pay typically runs $130,000–$160,000 across 483 roles with salary data.

Most-posted roles

View all roles at SpaceX

At a glance

TL;DR · Application Software Engineer, Inference

Apply Now Log in to save

As an Application Software Engineer at SpaceX in Palo Alto, you will join a dynamic team responsible for maintaining and enhancing the company’s high-performance AI inference platform. Your role involves designing and optimizing large-scale model serving systems end-to-end, from distributed infrastructure to deep low-level optimizations, ensuring reliable, high-throughput inference for mission-critical applications. You will work with Rust or C++ and other languages like Python and Go, leveraging technologies such as SGLang, vLLM, TensorRT-LLM, Kubernetes, Docker, and gRPC. This role demands expertise in full-stack development, distributed systems, GPU kernel optimizations, and service observability to tackle complex challenges at scale within SpaceX’s ambitious engineering goals.

Skills

Rust C++ SGLang vLLM TensorRT-LLM PostgreSQL ClickHouse MongoDB Docker Kubernetes gRPC Python Go CI/CD Triton

What you'll do

Develop highly reliable, high-throughput inference systems for SpaceX's AI models.
Architect and implement scalable distributed infrastructure for model serving.
Optimize latency and throughput of model inference under real production workloads.
Build reliable, high-concurrency serving systems with 100% uptime and low tail latency.
Benchmark, fine-tune, and accelerate inference engines using advanced techniques.

What we're looking for

1+ years of experience in full-stack or backend development with production systems.
Experience designing, implementing, and maintaining reliable distributed systems.
Proficiency in Rust or C++ for low-level system programming and optimizations.
Expertise in LLM inference engines and serving frameworks like SGLang, vLLM.
Deep knowledge of GPU kernels, batching, caching, parallelism, quantization techniques.

Similar roles

Software Engineer

Cisco

San Jose, CA 130 days ago $165,000–$277,600

SONiC-NOS Wireshark Python C++ Linux GDB IXIA Spirent High Speed Serdes MAC ports PRBS ANLT analyzers L2 switching networking protocols Cisco Silicon One

Save

Software Engineer

Austin, Texas 87 days ago

Python SQL AWS RESTful APIs Docker Kubernetes CI/CD Git PostgreSQL Redis GraphQL Swagger JUnit Selenium Jenkins Prometheus Grafana Ansible Terraform

Hybrid

Save

Software Engineer

Austin, Texas 17 days ago

AWS Python SQL C# .NET Vue Angular React HTML CSS JavaScript RESTful APIs MVVM SOLID principles Agile CI/CD Kubernetes Docker Terraform PostgreSQL Git Jenkins

Hybrid

Save