Member of Technical Staff, Model Serving - Remote

Overview

Join Cohere's mission to scale intelligence and serve humanity by building high-performance AI platforms for advanced NLP applications.

In Short

• Develop, deploy, and operate AI platforms for language models.
• Work on low latency, high throughput, and high availability environments.
• Interface with customers for customized deployments.
• Collaborate with various teams to optimize model performance.
• Contribute to the widespread adoption of AI technologies.
• Work in a diverse and inclusive environment.
• Enjoy a flexible work culture with remote options.
• Be part of a team passionate about AI research.
• Receive full health and dental benefits.
• Benefit from generous vacation and parental leave policies.

Requirements

• Experience with serving ML models in production.
• Experience in designing and maintaining production services at scale.
• Strong understanding of system behavior and resource estimation.
• Familiarity with deep learning model inference characteristics.
• Knowledge of computational characteristics of accelerators.
• Experience with distributed systems.
• Expertise in performance benchmarking and optimization.
• Experience with cloud infrastructure (AWS, GCP).
• Proficiency in Golang or similar high-performance languages.

Benefits

• Open and inclusive culture.
• Weekly lunch stipend and in-office snacks.
• Full health and dental benefits.
• Parental leave top-up for employees in select countries.
• Personal enrichment benefits.
• Remote-flexible work options.
• 6 weeks of vacation.