Software Engineer - Training/Inference (C++)

What this role involves

This role is for a software engineer on xAI's inference team, responsible for building and optimizing the high-performance inference platform that serves Grok to millions of users. The engineer will architect distributed infrastructure, optimize latency and throughput, and develop tools for tracing and debugging across the full stack. Required expertise includes low-level systems programming (C/C++ or Rust) and experience with GPU inference engines and system optimizations.

Skills this posting asks for

• c
• c++
• rust
• vllm
• sglang
• triton
• tensorrt-llm
• gpu kernels
• code generation
• quantization
• speculative decoding
• distillation
• low-precision numerics
• batching
• caching
• load balancing
• parallelism
• ci/cd
• benchmarking
• testing
• distributed systems
• high-concurrency
• model serving

From the employer’s posting

SpaceXAI’s mission is to create AI systems that can accurately understand the universe and aid humanity in its pursuit of knowledge. Our team i…