Member of Technical Staff, Pretraining evaluations

Who are we? Our mission is to scale intelligence to serve humanity. We’re training and deploying frontier models for developers and enterprises who are building AI systems to power magical experiences like content generation, semantic search, RAG, and agents. We believe that our work is instrumental to the widespread adoption of AI. We obsess over what we build. Each one of us is responsible for contributing to increasing the capabilities of our models and the value they drive for our customers. We like to work hard and move fast to do what’s best for our customers. Cohere is a team of researchers, engineers, designers, and more, who are passionate about their craft. Each person is one of the best in the world at what they do. We believe that a diverse range of perspectives is a requirement for building great products. Join us on our mission and shape the future Why this role? As a Member of Technical Staff in the pretraining evals team, you will play a key role in helping us make modelling decisions based on experimental outcomes for our large language models (LLMs). Your primary focus will be on developing better ways to measure base model progress. This can include implementing new/better evaluations for base model capabilities, finding ways to reduce noise in our current model evaluations, or developing evaluation benchmarks that measure model progress at all model scales, among other directions. This role combines expertise in statistics, data science, model evaluation and experience with base model capabilities and how to measure them. If any of these topics sound interesting to you, or if you believe that measuring model performance accurately is a crucial part of advancing artificial intelligence, we encourage you to apply. Please Note: We have offices in London, Paris, Toronto, San Francisco, and New York, but we also embrace being remote-friendly There are no restrictions on where you can be located for this role. As a Member of Technical Staff, Pretraining Evals you will: Deeply understand each individual evaluation task in our base model evaluation suite, have a clear idea of what each task measures and know their strengths and limitations. Suggest and implement improvements to our base model evaluation suite, whether by adding new tasks to measure unmeasured model capabilities or removing redundant or low-signal tasks. Improve the statistical understanding of our evals and improve the signal-to-noise ratio of our evaluation suite. You may be a good fit if you have: Familiarity with base model evaluations and how they differ from post-trained models. Strong statistical skills and experience evaluating scientific experiments related to data collection and model performance. Ability to convey statistical information effectively to a broad audience using visualizations and easy-to-understand numbers. Extremely strong software engineering skills. Proficiency in programming languages such as Python and ML frameworks (e.g., PyTorch, TensorFlow, JAX). Excellent communication skills to collaborate effectively with cross-functional teams and present findings. One or more papers at top-tier venues (such as NeurIPS, ICML, ICLR, AIStats, MLSys, JMLR, AAAI, Nature, COLING, ACL, EMNLP). If some of the above doesn’t line up perfectly with your experience, we still encourage you to apply We value and celebrate diversity and strive to create an inclusive work environment for all. We welcome applicants from all backgrounds and are committed to providing equal opportunities. Should you require any accommodations during the recruitment process, please submit an Accommodations Request Form, and we will work together to meet your needs. Full-Time Employees at Cohere enjoy these Perks: An open and inclusive culture and work environment Work closely with a team on the cutting edge of AI research Weekly lunch stipend, in-office lunches & snacks Full health and dental benefits, including a separate budget to take care of your mental health 100% Parental Leave top-up for up to 6 months Personal enrichment benefits towards arts and culture, fitness and well-being, quality time, and workspace improvement Remote-flexible, offices in Toronto, New York, San Francisco, London and Paris, as well as a co-working stipend ✈️ 6 weeks of vacation (30 working days) #J-18808-Ljbffr