Software Engineer, Inference (AI Data Engineering)
SpaceX
Location: Palo Alto, CA, United States
**Software Engineer, Inference (AI Data Engineering) at SpaceX in Palo Alto, CA, United States** **What you'll do** - Develop highly reliable, high-throughput inference systems for AI models - Architect and implement scalable distributed infrastructure for model serving - Optimize latency and throughput of model inference under production workloads - Build reliable serving systems with 100% uptime and excellent observability **What they're looking for** - Strong skills in distributed systems and low-level optimizations - Experience with GPU kernel work, quantization, and speculative decoding - Ability to own end-to-end components of serving systems - Knowledge of inference engines like SGLang, vLLM, TensorRT **Details** - Location: Palo Alto, CA, United States - Type: Not specified - Salary: null
Similar jobs in Palo Alto, CA
- Physical Design Engineer at SpaceX — Palo Alto, CA — SpaceX (Palo Alto, CA, United States)
- Accountant, AI Operations at SpaceX — Palo Alto, CA — SpaceX (Palo Alto, CA, United States)
- Internal Communications Manager at SpaceX — Palo Alto, CA — SpaceX (Palo Alto, CA, United States)
- Principal Security Software Engineer — SpaceX, Palo Alto, CA — SpaceX (Palo Alto, CA, United States)
- Full Stack Engineer at SpaceX — Palo Alto, CA — SpaceX (Palo Alto, CA, United States)
- Accounting Manager, Revenue at SpaceX — Palo Alto, CA — SpaceX (Palo Alto, CA, United States)
- Onboarding Specialist at SpaceX — Palo Alto, CA — SpaceX (Palo Alto, CA, United States)
- Software Security Engineer at SpaceX — Palo Alto, CA — SpaceX (Palo Alto, CA, United States)