Remote GPU Kernel Engineer for Low-Latency AI Inference

Anyone Ai Inc.; Santa Fe Capital; Remote; ARS 212,038,000 - 318,057,000; Full time

Job summary

Tether is seeking an AI Research Engineer (Kernel & Inference Optimization) to join its global, 100% remote team. You will drive innovation in model serving and inference architectures, with a focus on low-latency, scalable performance across edge devices.

A PhD/strong publication record in AI R&D is preferred, along with expertise in GPU kernels and MSL. You will design efficient inference pipelines, measure performance, and reduce memory footprints while collaborating with cross-functional

Qualifications

• PhD in NLP or ML preferred; solid AI R&D track record.
• Bachelor's in CS or related field required.

Responsibilities

• Design and deploy state-of-the-art model serving architectures delivering high throughput and low latency.
• Build, run, and monitor controlled inference tests in simulated and live environments.
• Identify and prepare high-quality test datasets and simulation scenarios for real-world deployment on low-resource devices.
• Analyze computational efficiency and diagnose bottlenecks in the serving pipeline.
• Collaborate with cross-functional teams to integrate optimized serving frameworks into production pipelines.
• Demonstrated ability to apply empirical research to optimize latency, throughput, and memory footprint.
• Understanding of Tensor Parallelism, Pipeline Parallelism, and Expert Parallelism for large models.
• Knowledge of Diffusion Models and Vision Transformers.

Skills

GPU kernels

Model serving

Inference optimization

Edge devices

MSL

Education

Master's or PhD in AI/ML

Bachelor's in Computer Science

Tools

Metal Shading Language (MSL)

Compute shaders

Mobile GPUs

Job description

Tether is seeking an AI Research Engineer (Kernel & Inference Optimization) to join its global, 100% remote team. You will drive innovation in model serving and inference architectures, with a focus on low-latency, scalable performance across edge devices.

A PhD/strong publication record in AI R&D is preferred, along with expertise in GPU kernels and MSL. You will design efficient inference pipelines, measure performance, and reduce memory footprints while collaborating with cross-functional