Staff Engineer - AI Inference & Benchmarking

Liquid-Ai; Boston (MA); Hybrid; USD 140,000 - 210,000; Full time

Benefits offered by this job

Equity

Health insurance

401(k) match

Unlimited PTO

Job summary

Liquid AI in Boston is seeking a Member Of Technical Staff, Infrastructure to own the inference engine layer and benchmarking infrastructure, collaborating with research and product teams and external partners. You will port models across runtimes, extend the llama.cpp/ONNX/MLX stack, design benchmarks, verify outputs, and help drive performance, reliability, and scalability across deployment targets.

This role blends systems work with hands-on verification of numerical correctness and

Qualifications

• Hands-on experience with inference frameworks going beyond basic usage.
• Experience designing and building benchmarking pipelines including methodology and reproducibility.
• Strong C++ and Python in performance-sensitive contexts.
• Solid understanding of inference fundamentals: quantization, decoding strategies, memory layout.

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 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.

Skills

C++

Python

Tools

llama.cpp

ONNX Runtime

MLX

Job description

Liquid AI in Boston is seeking a Member Of Technical Staff, Infrastructure to own the inference engine layer and benchmarking infrastructure, collaborating with research and product teams and external partners. You will port models across runtimes, extend the llama.cpp/ONNX/MLX stack, design benchmarks, verify outputs, and help drive performance, reliability, and scalability across deployment targets.

This role blends systems work with hands-on verification of numerical correctness and