Material World

Material World

Inference Performance Engineer

New York, NY

Sponsorship not specifiedDetected 69 days ago
PythonGoRustC++NLPLLMs

About the role

  • Serving frontier models at scale requires solving novel systems problems at every layer of the stack.

Responsibilities

  • Build and improve the inference runtime
  • Design scheduling, continuous batching, KV cache, and prefill/decode disaggregation
  • Implement low-precision kernels and speculative decoding
  • Drive throughput, latency, and cost per token
  • Collaborate with hardware teams on kernels, operators, and graph optimizations
  • Own the OpenAI-compatible API surface and serving protocol
  • Build benchmarking, profiling, and regression infrastructure
  • Relocation support

Requirements

  • Software engineering experience: Rust, Go, Python, or C++
  • Experience with model serving frameworks: vLLM, TGI, SGLang, TensorRT-LLM, llama.cpp, or custom runtimes
  • Experience with low-precision inference (FP8, FP4, INT4)

Compensation

  • Top-tier compensation structured to recognize and retain the best talent

Benefits

  • Meaningful equity
  • Comprehensive medical, dental, vision, life, and disability insurance
  • Parental leave for all new parents, including adoptive and surrogate journeys

Equal opportunity

  • We're an Equal Opportunity Employer and do not discriminate on the basis of any protected status under applicable law.

This listing is sourced directly from Material World's careers page and normalized into a canonical job model.