Remote AI Inference Kernel Engineer

Tuxcare Inc.; Rosario; Remote; ARS 184,482,000 - 292,096,000; Full time

Job summary

Tether is seeking an AI Research Engineer focused on Kernel and Inference Optimization. You will advance model serving pipelines and optimize performance across devices, from edge to cloud, driving low latency and scalable AI inference.

You should have deep expertise in Metal Shading Language, GPU kernels, and modern inference architectures, with a strong research-driven mindset and proven impact on throughput and memory efficiency.

Qualifications

• PhD in NLP/ML is preferred and publications in top conferences are a plus.
• Solid background in AI R&D with experience in model serving/isolation and deployment.
• Strong knowledge of kernel and inference optimization for mobile/edge devices.

Responsibilities

• Design and deploy state-of-the-art model serving architectures for high throughput and low latency.
• Build and monitor experiments to evaluate inference performance across domains.
• Identify bottlenecks and optimize memory, compute, and bandwidth usage.
• Collaborate with cross-functional teams to integrate optimized serving into production pipelines.
• Document results and define clear success metrics for real-world deployments.

Skills

GPU kernel programming

Model serving

Inference optimization

Low-level optimizations

Parallelism techniques

Education

PhD in NLP/ML (preferred)

BSc/MSc in Computer Science

Tools

Metal Shading Language (MSL)

GPU kernel frameworks

Job description

Tether is seeking an AI Research Engineer focused on Kernel and Inference Optimization. You will advance model serving pipelines and optimize performance across devices, from edge to cloud, driving low latency and scalable AI inference.

You should have deep expertise in Metal Shading Language, GPU kernels, and modern inference architectures, with a strong research-driven mindset and proven impact on throughput and memory efficiency.