ML Performance Engineer – Real-Time Inference

Odyssey; Palo Alto (CA); On-site; USD 130,000 - 160,000; Full time

Job summary

A leading AI lab in California seeks an experienced software engineer specialized in machine learning performance. Responsibilities include optimizing models used by extensive user bases, developing distributed training strategies, and collaborating closely with researchers to enhance model architectures. Ideal candidates should have over 8 years of software engineering experience, a strong background in ML optimization, and proficiency with tools like PyTorch and NVIDIA ecosystems. Join our innovative team to push the limits of AI technology.

Qualifications

• 8+ years of software engineering experience with focus on ML performance.
• Strong understanding of modern machine learning architectures.
• Ability to solve problems and adapt to new skills as necessary.

Responsibilities

• Optimize models for real-time usage by hundreds of thousands of users.
• Design and implement distributed training strategies.
• Partner with ML researchers to ensure model performance.
• Develop tools to identify performance bottlenecks.
• Pioneer innovative approaches to enhance performance metrics.

Skills

Performance optimization

Distributed training

Problem-solving

Deep learning architectures

PyTorch

NVIDIA GPU optimization

Job description

A leading AI lab in California seeks an experienced software engineer specialized in machine learning performance. Responsibilities include optimizing models used by extensive user bases, developing distributed training strategies, and collaborating closely with researchers to enhance model architectures. Ideal candidates should have over 8 years of software engineering experience, a strong background in ML optimization, and proficiency with tools like PyTorch and NVIDIA ecosystems. Join our innovative team to push the limits of AI technology.