Remote AI Kernel & Inference Optimization Engineer

Lever, Inc.; Turkey; Remote; TRY 450,000 - 850,000; Full time

Benefits offered by this job

Remote-first

International team

Cutting-edge AI research

Job summary

Lever, Inc. is seeking an AI Research Engineer (Kernel & Inference Optimization) based in Turkey to advance model-serving systems for diverse hardware environments.

You will design latency-focused architectures, develop GPU kernels, and push the performance of diffusion models and Vision Transformers across mobile and edge devices. You will collaborate with cross-functional teams in a remote, international setting to benchmark, test, and deploy optimized inference pipelines, ensuring scalable

Qualifications

• PhD in NLP, ML, or related field with strong AI research credentials.

Responsibilities

• Design and deploy high-throughput, low-latency model-serving architectures.

Skills

MSL (Metal Shading Language)

GPU kernels

Inference optimization

Distributed inference

Tensor, pipeline, expert parallelism

Diffusion models

Vision Transformers

Low-level systems optimization

Education

PhD in NLP/ML or related field

Job description

Lever, Inc. is seeking an AI Research Engineer (Kernel & Inference Optimization) based in Turkey to advance model-serving systems for diverse hardware environments.

You will design latency-focused architectures, develop GPU kernels, and push the performance of diffusion models and Vision Transformers across mobile and edge devices. You will collaborate with cross-functional teams in a remote, international setting to benchmark, test, and deploy optimized inference pipelines, ensuring scalable