Remote GPU Kernel & Inference Performance Engineer

Anyone Ai Inc.; La Pampa; A distancia; ARS 184.482.000 - 292.096.000; Jornada completa

Descripción de la vacante

Anyone Ai Inc. is seeking an AI Research Engineer focused on kernel and inference optimization. You will drive model serving innovations, optimize pipelines for edge AI, and tackle low-latency deployment across devices.

A strong background in Diffusion Models, Vision Transformers, and memory-efficient serving is essential. The role requires deep expertise in MSL, GPU kernel programming, and advanced inference techniques, with collaboration across teams to push the boundaries of on-device AI

Formación

• Advanced degree in Computer Science or related field.
• PhD in NLP, ML or related field with publications.
• Experience with low-level kernel and inference optimization on mobile devices.
• Proficiency in Metal Shading Language (MSL) and custom compute shaders.
• Strong background in model serving pipelines and inference frameworks.
• Familiarity with Diffusion Models and Vision Transformers.
• Experience with pruning, quantization, Flash attention, KV Cache, and speculative decoding.

Responsabilidades

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

Conocimientos

MSL

GPU kernels

Kernel optimization

Inference optimization

Diffusion Models

Vision Transformers

Quantization

Pruning

Flash attention

KV Cache

Speculative Decoding

Educación

Bachelor's in Computer Science

PhD in NLP/ML

Herramientas

Metal Shading Language (MSL)

Descripción del empleo

Anyone Ai Inc. is seeking an AI Research Engineer focused on kernel and inference optimization. You will drive model serving innovations, optimize pipelines for edge AI, and tackle low-latency deployment across devices.

A strong background in Diffusion Models, Vision Transformers, and memory-efficient serving is essential. The role requires deep expertise in MSL, GPU kernel programming, and advanced inference techniques, with collaboration across teams to push the boundaries of on-device AI