Remote AI Research Engineer – Model Serving & Inference

Anyone Ai Inc.; Rosario; Remote; ARS 276,723,000 - 368,964,000; Full time

Job summary

Tether seeks an AI Research Engineer focusing on kernel and inference optimization for edge devices. You will design efficient model serving pipelines and optimize for low latency and memory footprint across diverse hardware.

Join a globally distributed team, contributing to next-gen AI inference technologies and scalable architectures. Remote work worldwide, with emphasis on collaboration and publishing impact.

Qualifications

• Degree in Computer Science or related field; PhD in ML/NLP preferred with AI R&D publications.
• Knowledge of Metal Shading Language (MSL) and ability to write custom compute shaders.
• Proven mobile kernel/inference optimization experience with measurable latency improvements.
• Strong understanding of modern model serving architectures and memory-efficient design.
• Expertise in GPU kernels for mobile devices and end-to-end inference pipelines.

Responsibilities

• Design and deploy model serving architectures with high throughput and low latency.
• Build and monitor inference tests in simulated and production environments.
• Prepare test datasets and simulations for low-resource devices.
• Analyze bottlenecks and optimize serving pipelines for edge platforms.
• Collaborate with cross-functional teams to integrate optimized frameworks into production.

Skills

Kernel optimization

Inference optimization

GPU programming

Mobile GPU kernels

Model serving architectures

Diffusion models

Vision transformers

Education

Bachelor's degree in Computer Science or related field

PhD in ML/NLP preferred with publications

Tools

Metal Shading Language (MSL)

GPU compute shaders

Job description

Tether seeks an AI Research Engineer focusing on kernel and inference optimization for edge devices. You will design efficient model serving pipelines and optimize for low latency and memory footprint across diverse hardware.

Join a globally distributed team, contributing to next-gen AI inference technologies and scalable architectures. Remote work worldwide, with emphasis on collaboration and publishing impact.