Member of Technical Staff (AI Software Engineer, Agents)

Perplexity AI; San Francisco (CA); On-site; USD 140,000 - 200,000; Full time

Job summary

Perplexity AI is seeking an engineer to advance our agents platform. You will work across applied research and engineering to build capable AI agents that perform valuable tasks for millions of users.

You will train models, design secure data representations, and collaborate with cross-functional teams to deliver reliable, high-quality experiences across multiple environments including desktop and cloud.

Qualifications

• Strong Python proficiency with experience in ML workflows.
• Familiarity with browser automation and web tooling.
• Experience shipping user-facing AI features and agents.
• Ability to own features end-to-end in a fast-moving team.
• Proven product intuition and user experience focus.

Responsibilities

• Design AI agents to navigate digital environments and execute tasks.
• Train action and decision models for multimodal states and objectives.
• Ensure high-quality experiences across desktop, mobile, and cloud.
• Develop secure-by-design agent architectures and data representations.
• Collaborate with engineers, designers, PMs, and data scientists.
• Improve reliability, code quality, testing, and maintenance.

Skills

Python

TypeScript

Go

Rust

Browser technologies

AI/ML fundamentals

Product intuition

Ownership

Job description

• As an engineer on our Agents team, you will 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 will work across applied research and engineering to solve many open problems in AI, including:
• Designing AI agents to navigate the digital world and perform increasingly valuable units of work for our users
• Training action and decision models that determine, based on complex multimodal states, how to accomplish user-specified objectives
• Providing consistently excellent experiences across desktop, mobile, headless cloud, and other environments through flexible abstractions and frictionless backgrounding
• 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
• Engineer agent harnesses that connect powerful models with the environments and tools required to perform economically valuable work for users
• Drive cutting-edge AI capabilities across multiple layers of a rapidly growing product in the AI agents space
• Develop and leverage cutting-edge AI models, infrastructure, and browser technologies to advance the capability frontier and scale those capabilities for a rapidly growing userbase
• Ensure a high craft and quality bar, in both AI agent performance and user experience
• Collaborate with fellow engineers, designers, product managers, data scientists, and others across the company to integrate core Perplexity functionality into our frontier agentic products and vice-versa
• Contribute to product reliability, code quality, AI evaluation, testing, and maintenance across the broader team

• A passion for shipping products that surprise and delight
• Post-training and reinforcement learning (particularly for multimodal models)
• Significant experience in at least one of the following areas:
• Comfortable working with a small, fast-moving team, must be willing to dive in and take ownership
• Strong product intuition and taste for user experience excellence
• Proficiency in Python (bonus points for TypeScript, Go, and/or Rust)
• Browser technologies (CDP, Playwright, extension development, etc.)
• Strong foundational familiarity with the full AI product stack
• Context engineering and tool interfaces for frontier AI models