Lead Member of Technical Staff, Inference Infrastructure

The Lead Member of Technical Staff at Cohere is responsible for developing, deploying, and operating the AI platform delivering Cohere's large language models through easy to use API endpoints. The role involves providing technical leadership across multiple teams, driving the architecture and strategy for optimizing NLP models for production environments.

About the role

• Leading the design of high-performance, scalable, and reliable machine learning systems
• Setting technical direction and shaping the next generation of AI platforms powering advanced NLP applications
• Providing technical guidance to customers, designing customized deployments to meet their specific needs
• Mentoring engineers to raise the technical bar across the team

Responsibilities

• Technical leadership across multiple teams, driving the architecture and strategy for deploying optimized NLP models to production in low latency, high throughput, and high availability environments
• Leading the design, deployment, support, and troubleshooting of complex Linux-based computing environments at scale
• Owning compute/storage/network resource and cost management at an organizational level, including optimisation strategies
• Collaborating with cross-functional teams to build mission-critical systems
• Expertise in the computational characteristics of accelerators (GPUs, TPUs, and/or custom accelerators), and how to leverage them to drive latency and throughput improvements at scale
• Proficiency in Golang, C++, or other languages designed for high-performance scalable servers, with the ability to set coding standards and conduct senior-level technical reviews

Requirements

• 8+ years of engineering experience running production infrastructure at a large scale
• Track record of technical leadership
• Deep expertise with Kubernetes dev and production coding and support, including setting team-wide standards and best practices
• Extensive experience across GCP, Azure, AWS, OCI, and multi-cloud on-prem / hybrid serving environments, with the ability to guide strategic infrastructure decisions
• Proven ability to lead the design, deployment, support, and troubleshooting of complex Linux-based computing environments at scale
• Experience owning compute/storage/network resource and cost management at an organizational level, including optimisation strategies
• Exceptional collaboration and communication skills, with experience mentoring engineers and leading cross-functional initiatives to build mission-critical systems
• Strong expertise in the computational characteristics of accelerators (GPUs, TPUs, and/or custom accelerators), and how to leverage them to drive latency and throughput improvements at scale
• Deep knowledge of distributed systems, with experience establishing patterns and practices across engineering teams
• Proficiency in Golang, C++ or other languages designed for high-performance scalable servers, with the ability to set coding standards and conduct senior-level technical reviews

Qualifications

• Full-time employees at Cohere enjoy a weekly lunch stipend of $75/£75 or equivalent in your local currency for lunch
• Full health and dental benefits, including a separate budget for mental health
• RSP matching, 401K, Pension Scheme
• 100% Parental Leave top-up for up to 6 months, for either parent
• Annual enrichment benefits: Arts & culture, fitness/wellness, quality time, and a workspace improvement credit
• Education & learning stipend for conferences, courses, and coaching
• 6 weeks of paid vacation (30 working days!)
• Budget for traveling to other offices if you are remote, plus an annual company offsite