Remote GPU Kernel & Inference Engineer (Cuda/Triton)

Anyone Ai Inc.; Municipio de Rincón de los Sauces; Remote; ARS 181,906,000 - 303,177,000; Full time

Job summary

Tether is seeking an AI Research Engineer to advance kernel and inference optimization for scalable model serving across the globe in a 100% remote role.

You will design high-throughput, low-latency inference pipelines, optimize memory on edge devices, and implement novel serving strategies for multi-modal data.

Candidates with a PhD in NLP/ML and proven GPU kernel experience will help drive production readiness, benchmarks, and collaborative rigor in AI R&D.

Qualifications

• Degree in Computer Science or related field; PhD in NLP/ML preferred.
• Expertise in model serving and inference architectures.
• Experience with low-level kernel optimizations for mobile devices.
• Proven track record in low-latency, high-throughput inference.
• Strong publication record in AI R&D is a plus.

Responsibilities

• Design and deploy state-of-the-art model serving architectures with high throughput and low latency.
• Optimize memory usage across resource-constrained devices and edge platforms.
• Build, run, and monitor inference tests in simulated and live production environments.
• Identify test datasets and scenarios for low-resource deployment challenges.
• Analyze bottlenecks in serving pipelines and optimize performance.
• Collaborate with cross-functional teams to integrate optimized frameworks into production.

Skills

Model serving pipelines

Inference optimization

GPU kernels for mobile

Low-latency inference

Edge deployment

Benchmarks & metrics

Education

PhD in NLP/ML (preferred)

CS/related field degree

Tools

Metal Shading Language (MSL)

GPU kernel programming

Job description

Tether is seeking an AI Research Engineer to advance kernel and inference optimization for scalable model serving across the globe in a 100% remote role.

You will design high-throughput, low-latency inference pipelines, optimize memory on edge devices, and implement novel serving strategies for multi-modal data.

Candidates with a PhD in NLP/ML and proven GPU kernel experience will help drive production readiness, benchmarks, and collaborative rigor in AI R&D.