Staff Software Engineer, Speculative Decoding - Remote

Overview

A seasoned engineer role focused on developing high-performance algorithms for Generative AI inference, enhancing speed and accuracy in production-level AI systems.

In Short

• Design and implement speculative decoding algorithms.
• Optimize system architecture for large-scale AI model deployment.
• Develop high-performance codebases in C++ and Rust.
• Work within a Kubernetes-based environment.
• Collaborate with teams to improve model evaluation and scalability.
• Translate AI advancements into practical implementations.
• Provide technical leadership and mentorship.
• Drive performance improvements across the inference stack.
• Enhance efficiency in real-time AI processing.
• Contribute to a culture of innovation and continuous improvement.

Requirements

• Deep experience in Generative AI inference.
• Strong command of speculative decoding techniques.
• Proficiency in C++ and Rust.
• Experience with Kubernetes and distributed systems.
• Ability to work in a multi-process environment.
• Strong problem-solving skills.
• Experience in mentoring and leading teams.
• Passion for AI research and its application.
• Ability to translate research into production-ready solutions.
• Strong communication and collaboration skills.

Benefits

• Opportunity to work on cutting-edge AI technology.
• Collaborative and innovative work environment.
• Professional growth and development opportunities.
• Competitive salary and benefits package.
• Flexible working conditions.