Remote AI Kernel & Inference Engineer

Tuxcare Inc.; La Pampa; Remote; ARS 184,482,000 - 276,723,000; Full time

Job summary

Tether is seeking an AI Research Engineer (Kernel & Inference Optimization) to advance model deployment and inference strategies for edge devices. You will design high-throughput, low-latency pipelines, leveraging Metal Shading Language and GPU kernels, while optimizing memory usage and energy efficiency across diverse hardware.

The role emphasizes hands-on research, rigorous benchmarking, and collaboration with global teams to push the boundaries of AI serving on resource-constrained devices,

Qualifications

• Proven experience in low-level kernel optimizations and inference optimization on mobile devices.
• Strong background in model serving pipelines and inference frameworks.
• Experience with edge/on-device AI deployment and resource-constrained environments.

Responsibilities

• Design and optimize model serving pipelines for low-latency inference on edge devices.
• Develop and benchmark inference optimization techniques across multimodal architectures.
• Collaborate with cross-functional teams to integrate optimized serving into production pipelines.
• Analyze and reduce memory footprint while maintaining throughput and accuracy.
• Document experiments and provide performance metrics for production readiness.

Skills

Metal Shading Language

GPU kernels for mobile

low-level kernel optimizations

inference optimization

model serving architectures

edge deployment

diffusion models

vision transformers

pruning

quantization

flash attention

KV cache

speculative decoding

tensor parallelism

pipeline parallelism

expert parallelism

Education

PhD in NLP or ML

Computer Science degree

Job description

Tether is seeking an AI Research Engineer (Kernel & Inference Optimization) to advance model deployment and inference strategies for edge devices. You will design high-throughput, low-latency pipelines, leveraging Metal Shading Language and GPU kernels, while optimizing memory usage and energy efficiency across diverse hardware.

The role emphasizes hands-on research, rigorous benchmarking, and collaboration with global teams to push the boundaries of AI serving on resource-constrained devices,