We launched recruiters.rip, let your AI apply for you. First month free with code onemonthfree

Member of Technical Staff - GPU Inference Engineer

Liquid AI is an efficiency-first foundation-model company building device-native Liquid Foundation Models (LFMs) and tools to customize and deploy them.

Series A11 current maintainers9 active leads8 lead step-downs6 early lead departures
Cambridge, Massachusetts, United States
About Liquid AI

An MIT CSAIL spinout, Liquid AI develops general-purpose AI models focused on efficient deployment across CPUs, GPUs, NPUs, edge devices, and cloud or on-premises environments.

View jobs by Liquid AI

Skills

Candidate Availability

About the Role

You will join the team that owns the GPU serving stack built on vLLM and SGLang and make it faster and cheaper to run. You will be pointed at the most important inference bottleneck and carry it from profiling to a benchmarked result. You will speed up large-scale evaluation and synthetic data generation, benchmark the inference engine behind the API service, and integrate Liquid Foundation Models into vLLM, SGLang, and Hugging Face Transformers. You will work closely with researchers and engineers to diagnose throughput and latency problems.

Requirements

  • Hands-on experience running LLM inference on GPUs with a serving framework such as vLLM or SGLang, beyond default configuration
  • First-principles understanding of LLM inference: transformer forward pass, autoregressive decoding on a GPU, and latency, throughput, and memory trade-offs
  • Solid grasp of GPU fundamentals as they bear on inference
  • Experience profiling and benchmarking inference workloads
  • Strong Python and PyTorch, and comfort reading and changing large open-source codebases

Responsibilities

  • Own and improve the GPU serving stack on vLLM and SGLang, from configuration and scheduling to framework changes
  • Speed up large-scale evaluation and synthetic data generation and design the inference pipelines they run on
  • Select, profile, and benchmark the inference engine behind the API service and adapt the API layer around it
  • Integrate Liquid Foundation Models into vLLM, SGLang, and Hugging Face Transformers and maintain those integrations
  • Diagnose throughput and latency problems alongside researchers and serving engineers

Benefits

  • Equity
  • Unlimited PTO
  • Company-wide Refill Days
  • Comprehensive health coverage
  • Paid leave for pregnancy, parenting, medical needs, and caring for family