Paradigm is building a workspace that enables knowledge workers to use large language models to scale research through a simple, intuitive user interface. Its infrastructure orchestrates hundreds of thousands of agents to process millions of tokens per minute, compressing days of research into seconds. The engineering team addresses challenges involved in parallelizing agents at this scale, including simultaneous writes by large numbers of agents to a data model, real-time transmission of agent outputs across services to the client, and balancing write throughput with each agent’s in-memory footprint.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
Job Type
Full-time
Career Level
Senior
Education Level
No Education Listed