Perplexity is seeking energetic engineers to join our highly driven Agent Engine team. The Agent Engine team designs and builds powerful agentic experiences including Perplexity Computer, the Comet ecosystem, our Agent API, and more. In short, we build frontier intelligence systems for the world's most discerning users. As an engineer on our Agent Engine team, you'll bring AI expertise, sharp product intuition, and a tinkerer's mindset to advance the frontier of what agents can accomplish for our millions of devoted users. You'll work across engineering and applied research to solve many open problems in AI, including: - Designing frontier agent harnesses and systems to perform high-stakes, mission-critical work for our users; - Leveraging action and decision models that determine, based on complex multimodal states, how to accomplish user-specified objectives; - Providing consistently excellent experiences across local execution, headless cloud, custom executors, and other environments through sound system design and flexible abstractions; - Developing permission architectures, payload classifiers, and other methods to implement secure-by-design agentic capabilities; - Designing optimal data representations and modes of interaction between agents and their environments; - and much, much more. Qualifications - Strong foundational familiarity with the AI systems stack. - Proficiency in Python (bonus points for TypeScript, Go, and/or Rust). - Significant experience in at least one of the following areas: - Harness engineering - Agent Skills and plugin architectures - Model training and reinforcement learning - Browser technologies (CDP, Playwright, extension development, etc.) - Strong technical intuition and taste for user experience excellence. - Comfortable working with a small, fast-moving team; bias toward ownership. - A passion for shipping products that surprise and delight.
Summary
Build frontier agentic systems including Perplexity Computer, Comet ecosystem, and Agent API across local, cloud, and custom executors. Requires strong familiarity with the AI systems stack, proficiency in Python, and significant experience in harness engineering, agent skills, or model training.
Responsibilities
Designing frontier agent harnesses and systems; Leveraging action and decision models; Providing excellent experiences across local execution, headless cloud, custom executors; Developing permission architectures, payload classifiers
Qualifications
Strong foundational familiarity with the AI systems stack; Proficiency in Python (bonus points for TypeScript, Go, and/or Rust); Strong technical intuition and taste for user experience excellence
Experience requirements
Significant experience in at least one of the following areas: Harness engineering; Agent Skills and plugin architectures; Model training and reinforcement learning; Browser technologies