Remote AI Research Engineer: Kernel & Inference Optimization

Lever, Inc.; Netherlands; Remote; EUR 120,000 - 170,000; Full time

Benefits offered by this job

Remote-first team

International collaboration

Cutting-edge AI research projects

Flexible work environment

Job summary

Lever, Inc. in the Netherlands is seeking an AI Research Engineer (Kernel & Inference Optimization) to advance model-serving architectures across hardware environments.

You will tackle latency, throughput, and memory challenges on mobile and edge devices, developing GPU kernels and applying techniques like pruning and quantization.

This remote-first role combines research with systems engineering, collaborating with international teams to push efficient AI at scale.

Qualifications

• PhD in NLP/ML with strong AI research track record.
• Proven expertise in Metal Shading Language (MSL) and custom GPU kernels.
• Experience with latency, throughput and memory optimization on mobile/edge hardware.
• Experience with diffusion models and Vision Transformers.

Responsibilities

• Design and deploy advanced model-serving architectures for high throughput and low latency.
• Develop inference pipelines across mobile and edge environments.
• Establish performance targets and run controlled benchmarks.
• Develop custom GPU kernels and optimize memory usage.
• Collaborate with cross-functional teams in a remote, highly technical setting.

Skills

Latency optimization

Inference benchmarking

Model serving architectures

Diffusion models

Vision Transformers

Distributed inference

English communication

Education

PhD in NLP/ML (relevant)

Tools

MSL (Metal Shading Language)

GPU kernel programming

Pruning/Quantization

Job description

Lever, Inc. in the Netherlands is seeking an AI Research Engineer (Kernel & Inference Optimization) to advance model-serving architectures across hardware environments.

You will tackle latency, throughput, and memory challenges on mobile and edge devices, developing GPU kernels and applying techniques like pruning and quantization.

This remote-first role combines research with systems engineering, collaborating with international teams to push efficient AI at scale.