Senior Lead, Scalable ML Inference Infrastructure

Cohere; San Francisco (CA); Hybrid; USD 150,000 - 200,000; Full time

Benefits offered by this job

Open and inclusive culture

Weekly lunch stipend

Full health and dental benefits

Parental leave top-up

Personal enrichment benefits

6 weeks of vacation

Job summary

Cohere is seeking a Lead Member of Technical Staff in San Francisco to lead the design and deployment of high-performance, scalable machine learning systems. You will ensure optimal deployment of NLP models and mentor engineers while setting the technical direction. Ideal candidates have over 8 years of experience in production infrastructure and leading distributed systems. Enjoy perks like remote flexibility, 6 weeks of vacation, and a supportive work culture.

Qualifications

• 8+ years of engineering experience running production infrastructure at a large scale.
• Demonstrated experience leading the architecture and design of large, highly available distributed systems.
• Exceptional collaboration and communication skills, with experience mentoring engineers.

Responsibilities

• Provide technical leadership for deploying optimized NLP models to production.
• Lead the design of customized deployments to meet customer needs.
• Mentor engineers and drive architecture strategies across teams.

Skills

Production infrastructure experience

Technical leadership

Kubernetes expertise

Multi-cloud experience

Linux-based systems management

Collaboration and communication

Experience with GPUs/TPUs

Programming in Golang or C++

Job description

Cohere is seeking a Lead Member of Technical Staff in San Francisco to lead the design and deployment of high-performance, scalable machine learning systems. You will ensure optimal deployment of NLP models and mentor engineers while setting the technical direction. Ideal candidates have over 8 years of experience in production infrastructure and leading distributed systems. Enjoy perks like remote flexibility, 6 weeks of vacation, and a supportive work culture.