Skip to content
AI Engineer Jobs

Member of Technical Staff - GPU Inference Engineer

Liquid AI

Location
Hybrid (San Francisco, California)
Employment
Full-time
Level
Mid Level
Posted 3 days ago

About the role

Liquid AI, spun out of MIT CSAIL, builds efficient general-purpose AI systems for diverse deployment targets. This role involves owning and optimizing the GPU serving stack to improve inference performance and cost-efficiency for their foundation models.

Skills

GPU inference vLLM SGLang Python PyTorch LLM inference Transformer architecture Autoregressive decoding GPU profiling Benchmarking Inference pipelines Latency optimization Throughput optimization Hugging Face Transformers

Benefits

  • Unlimited PTO
  • Health Coverage
  • Paid Parental Leave
  • Paid Family Leave

Perks

  • Equity
  • Hybrid Work
  • Refill Days

Full job details