Remote AI Inference Kernel Engineer — Edge & Low-Latency

Tuxcare Inc.; Quilmes; A distancia; ARS 185.819.000 - 278.728.000; Jornada completa

Descripción de la vacante

Tether is seeking an AI Research Engineer to advance kernel and inference optimization for edge and cloud deployments. You will optimize model serving pipelines, design low-latency GPU kernels, and push the boundaries of on-device AI.

The role covers resource-constrained devices, multi-modal models, and scalable architectures, with collaboration across teams. A PhD is preferred; strong C++/CUDA and MSL experience is expected.

Formación

• Bachelor's degree in Computer Science or related field required.
• PhD in NLP/ML or related field preferred.
• Strong experience in model serving pipelines and inference optimization.

Responsabilidades

• Design and deploy state-of-the-art model serving architectures with high throughput and low latency.
• Build and monitor controlled inference tests in simulated and live environments.
• Identify and prepare test datasets and scenarios for real-world edge deployment.
• Analyze bottlenecks in serving pipelines and optimize memory and compute usage.
• Collaborate with cross-functional teams to integrate optimized serving frameworks into production pipelines.

Conocimientos

Kernel Optimization

Inference Optimization

Model Serving

GPU Kernels

Edge Inference

Low Latency

Diffusion Models

Vision Transformers

Pruning

Quantization

Educación

Degree in Computer Science or related field

PhD in NLP/ML or related field

Herramientas

Metal Shading Language (MSL)

Descripción del empleo

Tether is seeking an AI Research Engineer to advance kernel and inference optimization for edge and cloud deployments. You will optimize model serving pipelines, design low-latency GPU kernels, and push the boundaries of on-device AI.

The role covers resource-constrained devices, multi-modal models, and scalable architectures, with collaboration across teams. A PhD is preferred; strong C++/CUDA and MSL experience is expected.