Member of Technical Staff Inference Systems
Liquid AIVisit Liquid AI website
Liquid AI is an efficiency-first foundation-model company building device-native Liquid Foundation Models (LFMs) and tools to customize and deploy them.
Cambridge, Massachusetts, United States
Funding history
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.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will build benchmark suites for inference performance, model quality, and knowledge evaluation across hardware targets. You will validate partner solutions, port models to runtimes and frameworks, extend the inference engine, and make benchmark results reproducible and trustworthy.
Requirements
- Hands-on experience with llama.cpp, ONNX Runtime, MLX, or a similar inference framework
- Experience designing benchmarking pipelines, methodology, validation, and reproducibility
- Strong C++ and Python skills in performance-sensitive contexts
- Understanding of quantization, decoding strategies, memory layout, and inference fundamentals
Responsibilities
- Design and build benchmark suites across hardware targets
- Evaluate external partner solutions and deliver findings
- Port models onto runtimes and frameworks and verify correctness
- Maintain and extend the inference engine layer
- Make benchmark results explainable, verifiable, and reproducible
Benefits
- Equity
- Medical, dental, and vision premiums fully paid for employees and dependents
- 401(k) matching up to 4% of base pay
- Unlimited PTO
- Company-wide Refill Days