Member of Technical Staff - GPU Inference Engineer
Liquid AI · San Francisco
Frontier labonsite
At a glance
Highlights
- Own the GPU serving stack and make inference faster and cheaper.
- Speed up large-scale evaluation and synthetic data generation pipelines.
- Tune the inference engine powering the API service with benchmarks.
What they offer
- Competitive base salary plus equity
- Unlimited PTO plus company-wide Refill Days
- Comprehensive health coverage
- Paid leave for pregnancy, parenting, medical and family care
Ideal candidate
First-principles problem solver who owns bottlenecks end-to-end and makes research teams faster. You care about measured throughput and low-cost serving over framework defaults.
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, and latency, throughput and memory trade-offs
- Solid grasp of GPU fundamentals as they bear on inference
- Experience profiling and benchmarking inference workloads and acting on results
- Strong Python and PyTorch, and comfort reading and changing large open-source codebases
Lab profile
About Liquid AI
MIT CSAIL spinout building efficient general-purpose AI for cloud to edge.
What they build
- Liquid Foundation Models
- LFM2.5-Audio
Known for
- Efficiency-first foundation models
- Data center to on-device deployment
- Low latency with minimal memory usage
- Liquid Neural Networks architecture
Key facts
- Spun out of MIT CSAIL
Posted · Last seen