Remote AI Research Engineer: Kernel & Inference Optimization

Lever, Inc.; México; A distancia; MXN 900.000 - 1.500.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Remote-first team

International collaboration

Cutting-edge AI research challenges

Descripción de la vacante

Lever, Inc. is seeking an AI Research Engineer (Kernel & Inference Optimization) based in Mexico.

You will work at the intersection of AI research, systems engineering, and high-performance model inference, focusing on latency, throughput, and memory efficiency across hardware environments. You will develop and optimize model-serving architectures, write custom GPU kernels (MSL), and collaborate with cross-functional teams to translate research into production edge applications.

Formación

• Degree in Computer Science or related field; PhD in NLP/ML highly relevant.
• Proven expertise in Metal Shading Language (MSL) and writing custom compute shaders.
• Experience with low-level kernel optimization and inference optimization on mobile/edge devices.
• Track record of measurable improvements in latency, throughput, and memory footprint.
• Knowledge of modern model-serving architectures and optimization techniques for high-performance AI deployment.

Responsabilidades

• Design and deploy advanced model-serving architectures optimized for high throughput and low latency.
• Develop inference pipelines across diverse environments including edge devices.
• Establish performance targets for latency, throughput, memory footprint, and reliability.
• Build controlled inference benchmarks and track latency, throughput, and errors.
• Create datasets and simulation scenarios to evaluate model performance.
• Identify bottlenecks and apply system-level optimizations like batching and memory management.
• Develop custom GPU kernels and compute shaders for mobile hardware (MSL).
• Apply pruning, quantization, Flash Attention, KV caching, and speculative decoding.
• Design distributed inference using tensor/pipeline/expert parallelism for large-scale GPUs.
• Collaborate with cross-functional teams to integrate optimized inference frameworks.
• Define evaluation methodologies and document experimental results.
• Monitor production performance to identify improvement opportunities.

Conocimientos

MSL kernel programming

GPU kernel optimization

Inference optimization

Distributed inference

Benchmarking

English communication

Educación

PhD in NLP or Machine Learning

Herramientas

MSL (Metal Shading Language)

Descripción del empleo

Lever, Inc. is seeking an AI Research Engineer (Kernel & Inference Optimization) based in Mexico.

You will work at the intersection of AI research, systems engineering, and high-performance model inference, focusing on latency, throughput, and memory efficiency across hardware environments. You will develop and optimize model-serving architectures, write custom GPU kernels (MSL), and collaborate with cross-functional teams to translate research into production edge applications.