Inference Systems Engineer: Benchmarking & Porting (Hybrid)

Liquid AI; Boston (MA); Hybrid; USD 180,000 - 240,000; Full time

Benefits offered by this job

Equity

Health insurance

401(k) matching

Unlimited PTO

Refill Days

Job summary

Liquid AI in Boston is seeking a Member Of Technical Staff, Infrastructure to join our Research & Engineering team. You will design benchmark suites and verify inference performance across hardware targets.

Port models like LFM2, extend the inference engine on llama.cpp, ONNX and MLX, and ensure correctness end-to-end while collaborating with research and product.

The role emphasizes hands-on work with C++ and Python in performance-sensitive contexts.

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.

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.

Skills

C++

Python

Inference frameworks

Benchmarking pipelines

Tools

llama.cpp

ONNX Runtime

MLX

Job description

Liquid AI in Boston is seeking a Member Of Technical Staff, Infrastructure to join our Research & Engineering team. You will design benchmark suites and verify inference performance across hardware targets.

Port models like LFM2, extend the inference engine on llama.cpp, ONNX and MLX, and ensure correctness end-to-end while collaborating with research and product.

The role emphasizes hands-on work with C++ and Python in performance-sensitive contexts.