Job Title

OverviewMember of Technical Staff, Integration/RL Team (Research Engineer) at Cohere. Join to apply for the Member of Technical Staff, Integration/RL Team (Research Engineer) role at Cohere.Our mission is to scale intelligence to serve humanity. Were 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 and each person contributes to increasing the capabilities of our models and the value they drive for our customers. Cohere is a team of researchers, engineers, designers, and more who are passionate about their craft and value a diverse range of perspectives as a foundation for building great products. Join us on our mission and shape the future!The integration team is responsible for developing and scaling machine learning algorithms and infrastructure for LLM post-training, with a focus on large-scale, distributed RL methods. We strive for excellence in both engineering and science by meticulously designing experiments and design docs. Tasks are assigned according to expertise, with a global team effort to write production code and support research efforts, depending on interests and organizational needs. This role aims to enhance the global quality of the post-training codebase by implementing new tools to ease and support research, optimizing post-training algorithms, and scaling distributed RL to unprecedented levels. We have offices in London, Paris, Toronto, San Francisco, New York, and we are remote-friendly. Applicants may work anywhere between UTC06:00 and UTC+01:00.As a Member Of Technical Staff, You WillDesign and write high-performing and scalable software for training models.Develop new tools to support and accelerate research and LLM training.Coordinate with other engineering teams (Infrastructure, Efficiency, Serving) and the scientific teams (Agent, Multimodal, Multilingual, etc.) to create an integrated post-training ecosystem.Craft and implement techniques to improve performance and speed up training cycles, including SFT, offline preference, and the RL regime.Research, implement, and experiment with ideas on our cluster and data infrastructure.Collaborate with scientists, engineers, and teams to advance research and production goals.You Are An Ideal Candidate If You HaveExtremely strong software engineering skills.Value test-driven development, clean code, and reducing technical debt at all levels.Proficiency in Python and ML frameworks such as JAX, PyTorch and/or XLA/MLIR.Experience using and debugging large-scale distributed training strategies (memory/speed profiling).(Bonus) Experience with distributed training infrastructures (Kubernetes) and related frameworks (Ray).(Bonus) Hands-on experience with post-training phase of model training, with emphasis on scalability and performance.(Bonus) Experience in ML, LLM and RL academic research.This Role Is Perfect For You If YouHave a deep passion for quality work.Enjoy tuning and optimizing large LLM models.Are comfortable collaborating with colleagues across different levels of software engineering skills.Are comfortable diving into complex ML codebases to identify and resolve issues and ensure smooth operation of systems. Thrive in a fast-paced, technically challenging environment, contributing innovative ideas and solutions.We value and celebrate diversity and strive to create an inclusive work environment for all. Should you require accommodations during the recruitment process, please submit an Accommodations Request Form, and we will work together to meet your needs.BenefitsFull-Time employees enjoy an open and inclusive culture and work environmentWork closely with a team on the cutting edge of AI researchWeekly lunch stipend, in-office lunches and snacksFull health and dental benefits, including a separate budget for mental health100% Parental Leave top-up for 6 months for employees based in Canada, the US, and the UKPersonal enrichment benefits towards arts and culture, fitness and well-being, and workspace improvementRemote-flexible, offices in Toronto, New York, San Francisco and London with a co-working stipend6 weeks of vacationNote: This post is co-authored by both Cohere humans and Cohere technology.Seniority levelMid-Senior levelEmployment typeFull-timeJob functionEngineering and Information TechnologyIndustriesSoftware Development #J-18808-Ljbffr