Remote GPU Kernel & Inference Engineer

Anyone Ai Inc.; Ciudad de Mendoza; Remote; ARS 181,747,000 - 272,620,000; Full time

Job summary

Tether is hiring an AI Research Engineer to advance model serving and inference optimization for diverse AI systems in a fully remote worldwide setup. You will work on kernel- and edge-optimized architectures, from mobile GPU kernels to distributed inference pipelines, tackling latency, memory, and throughput challenges.

You should have a PhD or strong track record in AI research, with expertise in MSL, Diffusion Models, and Vision Transformers, and be comfortable delivering production-grade

Qualifications

• Deep expertise in designing and optimizing model serving pipelines.
• Strong background in inference optimization for mobile and edge devices.
• Experience with low-level kernel optimizations and GPU programming.

Responsibilities

• Design and deploy state-of-the-art model serving architectures with high throughput and low latency.
• Build, test, and monitor inference pipelines across diverse environments including edge devices.
• Analyze bottlenecks, memory usage, and latency to optimize production serving.
• Collaborate with cross-functional teams to integrate optimized inference frameworks.
• Drive measurable improvements in real-world AI performance on resource-constrained systems.

Skills

Metal Shading Language (MSL)

GPU kernels for mobile devices

Model serving architectures

Inference optimization

Low-latency / high-throughput

Edge / on-device AI

Diffusion Models knowledge

Vision Transformers knowledge

Quantization / Pruning

Education

Bachelor's degree in Computer Science or related field

PhD in NLP or Machine Learning (preferred)

Job description

Tether is hiring an AI Research Engineer to advance model serving and inference optimization for diverse AI systems in a fully remote worldwide setup. You will work on kernel- and edge-optimized architectures, from mobile GPU kernels to distributed inference pipelines, tackling latency, memory, and throughput challenges.

You should have a PhD or strong track record in AI research, with expertise in MSL, Diffusion Models, and Vision Transformers, and be comfortable delivering production-grade