Lead Member of Technical Staff – Inference Infrastructure

About the role

Cohere is looking for a senior technical leader to shape the next generation of AI platforms that serve large language models via low‑latency, high‑throughput APIs. You will guide architecture, drive performance, and mentor engineers across multiple teams.

Key responsibilities

• Provide technical leadership across multiple teams to design high‑performance, scalable ML systems.
• Drive architecture and strategy for deploying optimized NLP models in low‑latency, high‑availability environments.
• Act as a primary point of contact for customers, designing customized deployments to meet specific needs.
• Mentor engineers, raise the technical bar, and establish best practices for production infrastructure.

Required profile

• 8+ years of engineering experience running production infrastructure at large scale.
• Proven track record of leading architecture and design of highly available distributed systems.
• Deep expertise with Kubernetes, GPU workloads, and multi‑cloud environments (GCP, Azure, AWS, OCI).
• Strong experience managing compute, storage, network resources and cost optimization.
• Excellent collaboration, communication, and mentorship abilities.

Required skills

• Kubernetes
• GPU/TPU workloads
• GCP, Azure, AWS, OCI
• Linux systems
• Distributed systems
• Golang
• C++

What we offer

• Weekly lunch stipend of $75 (or equivalent).
• Full health, dental, and mental‑health benefits.
• RRSP matching, 401(k), pension scheme.
• 100% parental leave top‑up for up to 6 months.
• Annual enrichment budget for arts, fitness, and workspace improvements.
• Education stipend for conferences, courses, and coaching.
• 6 weeks paid vacation and travel budget for office visits.