Recruit Detail
Find out more about the work we do, the experience and skills we can bring to the table, and our terms and conditions.
Company Name
CyberAgent, Inc.
Job Type
[AI Lab] Research Engineer (Reinforcement Learning)
Work Detail
■Mission The Reinforcement Learning Team aims for the "practical application of reinforcement learning," undertaking a wide range of activities from theoretical research to solving real-world problems. This effort goes beyond simply publishing papers; it also aims to create practical value, with a particular focus on reinforcement learning in the field of generative AI. In this field, the development and experimentation of Large Language Models (LLM) and Reinforcement Learning from Human Feedback (RLHF) are central. Research Engineers (Reinforcement Learning) collaborate with research scientists, playing a crucial role in the engineering aspects of the project, working throughout the entire process from algorithm development to implementation. ■Main Tasks Research and development of reinforcement learning and RLHF technologies for improving the performance of language models Algorithm implementation, experimentation, and results analysis Data collection, preprocessing, and dataset construction Creation of demos and prototypes
Ideal Profile
[Required Skills] * Deep understanding and practical experience in reinforcement learning or language generation AI * Programming ability using Python [Preferred Skills] * Experience in experimentation and application development using language generation models * Experience using the Huggingface Transformers library * Development experience using container technologies (such as Docker) * Experience in designing and conducting proof-of-concept experiments [Desired Candidate Profile] * Passionate about the social implementation of reinforcement learning and language generation AI, and a desire to contribute to its practical application * Self-motivated individuals who can solve problems through trial and error based on data analysis * Individuals who can actively discuss and collaborate with other members to continuously improve experiments and implementations
Work Location
150-6121 2-24-12 Shibuya, Shibuya-ku, Tokyo, Shibuya Scramble Square 22F
Phd. Stating Salary
Negotiable Compensation will be determined based on experience and abilities, in accordance with company regulations.