Remote AI Research Engineer: Kernel & Inference

Visa Hunt; Germany (OH); On-site; USD 150,000 - 230,000; Full time

Job summary

Tether is seeking a specialist to advance AI model serving and inference for edge and on-device applications. You will design pipelines that deliver high throughput with minimal memory footprints across diverse platforms.

You will optimize latency, throughput, and energy use while developing robust evaluation frameworks and collaborating with cross-functional teams to deploy production-ready solutions.

Qualifications

• PhD in NLP or related field with strong AI R&D track record.
• Experience in low-latency model serving and inference.
• Knowledge of Metal Shading Language (MSL) and GPU kernels.
• Background in edge/mobile deployment and performance optimization.

Responsibilities

• Design and deploy state-of-the-art model serving architectures with high throughput and low latency.
• Build and monitor inference tests in simulated and live environments.
• Prepare test datasets for real-world deployment on low-resource devices.
• Analyze bottlenecks in serving pipelines and optimize memory usage.
• Collaborate with cross-functional teams to integrate optimized serving in production.

Skills

NLP R&D

Model serving

Inference optimization

GPU kernels

Edge devices

MSL

Mobile GPUs

Education

PhD in NLP

CS degree

Tools

Metal

Shaders

TensorRT

ONNX

Job description

Tether is seeking a specialist to advance AI model serving and inference for edge and on-device applications. You will design pipelines that deliver high throughput with minimal memory footprints across diverse platforms.

You will optimize latency, throughput, and energy use while developing robust evaluation frameworks and collaborating with cross-functional teams to deploy production-ready solutions.