Remote AI Kernel & Inference Engineer

Anyone Ai Inc.; La Pampa; A distancia; ARS 184.482.000 - 276.723.000; Jornada completa

Descripción de la vacante

Tether is seeking an AI Research Engineer to advance kernel and inference optimization for next-generation AI systems. You will design and refine model serving pipelines, targeting low latency and efficient memory usage across diverse hardware, including edge and mobile devices.

Responsibilities span building robust inference tests, benchmarking, and collaborating with cross-functional teams to deploy production-grade solutions. A PhD in NLP/ML is advantageous.

Formación

• Degree in Computer Science or related field.
• PhD in NLP/ML preferred.
• Knowledge of Metal Shading Language (MSL) required.
• Experience in low-level kernel and inference optimization on mobile devices.
• Strong research background with publications in AI/ML.

Responsabilidades

• Design and deploy state-of-the-art model serving architectures with high throughput and low latency.
• Build, run, and monitor controlled inference tests in simulated and live production environments.
• Identify and prepare high-quality test datasets and simulation scenarios for real-world deployment.
• Analyze computational efficiency and diagnose bottlenecks in the serving pipeline.
• Collaborate with cross-functional teams to integrate optimized serving frameworks into production pipelines for edge devices.
• Demonstrated ability to apply empirical research to improve inference performance and system efficiency.

Conocimientos

Kernel optimization

Inference optimization

GPU kernel coding (MSL)

Model serving architectures

Edge/limited hardware awareness

Diffusion models

Vision transformers

Educación

Degree in Computer Science

PhD in NLP or ML

Descripción del empleo

Tether is seeking an AI Research Engineer to advance kernel and inference optimization for next-generation AI systems. You will design and refine model serving pipelines, targeting low latency and efficient memory usage across diverse hardware, including edge and mobile devices.

Responsibilities span building robust inference tests, benchmarking, and collaborating with cross-functional teams to deploy production-grade solutions. A PhD in NLP/ML is advantageous.