Remote GPU Kernel & Inference Engineer

Anyone Ai Inc.; Rosario; Remote; ARS 215,229,000 - 322,843,000; Full time

Job summary

Tether invites you to join an AI model team focused on kernel and inference optimization for cutting-edge AI systems. You will design and deploy high-throughput, low-latency serving pipelines and advance multi-modal architectures for edge and on-device deployment.

Candidate must have deep expertise in model serving, GPU kernels, and MSLS; PhD in NLP/ML preferred and a track record of publications. This fully remote role welcomes worldwide applicants.

Qualifications

• A PhD in NLP or ML with publications in AI/ML conferences is preferred.
• Solid track record in AI R&D and industry-relevant projects.
• Knowledge of Metal Shading Language (MSL) and shader programming.

Responsibilities

• Design and deploy state-of-the-art model serving architectures for high throughput and low latency.
• Optimize inference pipelines and memory usage across edge and on-device platforms.
• Develop and test novel serving strategies and inference algorithms.
• Identify bottlenecks and quantify performance with robust metrics.
• Collaborate with cross-functional teams to integrate optimized pipelines into production.

Skills

MSL knowledge

Kernel optimization

Inference optimization

GPU kernels

Edge/On-device

Model serving

Research-driven

Education

PhD in NLP/ML

Computer Science degree

Tools

Metal Shading Language (MSL)

Job description

Tether invites you to join an AI model team focused on kernel and inference optimization for cutting-edge AI systems. You will design and deploy high-throughput, low-latency serving pipelines and advance multi-modal architectures for edge and on-device deployment.

Candidate must have deep expertise in model serving, GPU kernels, and MSLS; PhD in NLP/ML preferred and a track record of publications. This fully remote role welcomes worldwide applicants.