Member Of Technical Staff, Model Efficiency (AI)

TL;DR

Member Of Technical Staff, Model Efficiency (AI): Developing and optimizing high-performance ML systems for large language models with an accent on improving inference efficiency and performance metrics. Focus on diagnosing bottlenecks, implementing optimizations, and collaborating across teams.

Location: Remote (preferred in EST and PST time zones)

Company

Cohere is focused on training and deploying frontier models for AI systems.

What you will do

• Work on improving core performance metrics across the inference stack.
• Identify bottlenecks and develop optimizations for model execution.
• Collaborate with modeling and systems teams to implement improvements.
• Build expertise in advanced performance techniques, including GPU/CUDA optimizations.
• Experiment and measure impact of optimizations in production.

Requirements

• 5+ years of experience in writing high-performance, production-quality code.
• Strong programming skills in C++ or Python.
• Experience with large language models and LLM inference ecosystem.
• Ability to diagnose and resolve performance bottlenecks.
• A strong bias for action and fast shipping of improvements.

Nice to have

• Experience with GPU programming and CUDA.
• Knowledge of language modeling with transformers.
• Experience in scaling performance-critical distributed systems.

Culture & Benefits

• Open and inclusive culture and work environment.
• Work closely with a cutting-edge AI research team.
• Weekly lunch stipend and in-office lunches.
• Full health and dental benefits.
• 100% Parental Leave top-up for up to 6 months.
• 6 weeks of vacation (30 working days).