Remote GPU Kernel & Inference Optimization Engineer

Anyone Ai Inc.; Quilmes; Remote; ARS 184,482,000 - 292,096,000; Full time

Job summary

Tether is hiring an AI Research Engineer (Kernel & Inference Optimization) to lead model serving and optimization for scalable AI systems. The role focuses on deploying efficient inference pipelines across edge and device environments, delivering high throughput with low latency.

You will work on resource-constrained deployments, multi-modal architectures, and novel serving strategies, collaborating with a global remote team. A PhD in NLP/ML or related field is highly valued.

Qualifications

• PhD in NLP/ML or related field is preferred.
• Strong background in AI R&D and publications.
• Deep expertise in model serving and inference optimization.

Responsibilities

• Design and deploy high-throughput model serving architectures.
• Optimize memory usage for edge and device deployments.
• Build and monitor inference tests in simulated and live environments.
• Identify bottlenecks and improve latency, throughput, memory footprint.
• Collaborate with cross-functional teams to productionize optimized frameworks.

Skills

GPU kernel programming

Model serving

Inference optimization

Edge deployment

Diffusion Models

Education

PhD in NLP/ML or related field

Computer Science degree

Tools

Metal Shading Language (MSL)

Compute shaders

Job description

Tether is hiring an AI Research Engineer (Kernel & Inference Optimization) to lead model serving and optimization for scalable AI systems. The role focuses on deploying efficient inference pipelines across edge and device environments, delivering high throughput with low latency.

You will work on resource-constrained deployments, multi-modal architectures, and novel serving strategies, collaborating with a global remote team. A PhD in NLP/ML or related field is highly valued.