← All roles

Member of Technical Staff - Inference Systems

Liquid AI· Research & Engineering
Apply on company site
Hybrid (Boston)Full-timePosted 1mo ago

About the role

Role focused on designing, building, and validating the inference engine and benchmarking stack for production models, with emphasis on evaluation across hardware targets, portability of models across runtimes, and partner-facing verification.

Responsibilities

  • Design and build benchmark suites that cover inference performance, model quality, and knowledge evaluation across different hardware targets.
  • Run external partner verifications: evaluate their solutions against our benchmarks, identify gaps, and clearly deliver findings.
  • Port models like LFM2 onto different runtimes and frameworks, and verify correctness end-to-end.
  • Maintain and extend the inference engine layer built on llama.cpp, ONNX, and MLX as new model architectures emerge from research.
  • Make benchmark results explainable and verifiable, so internal teams and partners can trust and reproduce them independently.

Qualifications

  • Hands-on experience with at least one inference framework like llama.cpp, ONNX Runtime, or MLX, going beyond basic usage into internals and modification.
  • Experience designing and building benchmarking pipelines, including methodology, validation, and reproducibility.
  • Strong C++ and Python in performance-sensitive contexts.
  • Solid understanding of inference fundamentals: quantization, decoding strategies, memory layout, and how they interact.

Skills

Required:Inference framework proficiencyBenchmarking pipeline designC++PythonInference fundamentals

Benefits

  • Compensation: Competitive base salary with equity in a unicorn-stage company
  • Health: We pay 100% of medical, dental, and vision premiums for employees and dependents
  • Financial: 401(k) matching up to 4% of base pay
  • Time Off: Unlimited PTO plus company-wide Refill Days throughout the year
Last updated Sep 2, 2026. Interested? Apply on the company site.
Liquid AI logo

About Liquid AI

Build efficient general-purpose AI at every scale.

We build efficient general-purpose AI at every scale. Liquid Foundation Models (LFMs) are a new generation of generative AI models that achieve state-of-the-art performance at every scale, while maintaining a smaller memory footprint and more efficient inference.

AIEdge AIFoundation ModelsGenerative AIliquid-ai-recruiting-target
Company profileWebsite

More open roles at Liquid AI