Member of Technical Staff (Applied AI Engineer, Agent Capabilities)

The role

This person will evaluate frontier models and turn advances into production agent systems. They will improve agent abilities in planning, tool use, and task completion while building scalable capabilities and reliable infrastructure.

What you will do

• Evaluate frontier models against real user tasks and turn advances into production agent systems.
• Improve agents ability to plan, use tools, manage context, recover from errors, and complete long-running tasks.
• Apply ML and LLM techniques to design scalable agent capabilities like skills, plugins, and multi-agent collaboration.
• Own agent behavior end-to-end from user-facing products to backend services.
• Define offline and online evaluations for task completion, correctness, safety, latency, cost, and user satisfaction.
• Build secure, observable, and reliable agent systems including permissions and safeguards.
• Develop tracing, replay, and monitoring infrastructure.
• Collaborate with PM, Data Science, and Research to turn complex agent behaviors into product experiences.
• Apply advances in models, inference, evaluation, and agent architecture to production performance.
• Set technical direction and provide mentorship and technical leadership.

Required qualifications

• Typically 6+ years of professional software engineering experience building and owning robust AI-powered, large-scale, user-facing or data-intensive products.
• Strong software engineering fundamentals with experience building and operating AI/ML products, backend services, or distributed systems at scale.
• Experience owning the AI product lifecycle including data analysis, evaluation, production monitoring, and iterative improvement.
• Practical experience in one or more relevant areas such as agent harnesses, tool use, context engineering, model evaluation, browser automation, or long-running task execution.
• Strong product judgment and execution to translate ambiguous user needs into applied AI or ML problems.
• Genuine interest in frontier AI capabilities, agent systems, and productizing new model behaviors.

Nice to have

• Experience with LLM context engineering or harness engineering
• Experience with subagents, coding assistants, long-running or autonomous task execution
• Deep familiarity with the strengths and limitations of current model families
• Experience building agent permissions, safeguards, evaluation infrastructure, or production observability systems
• Experience with mid-training, post-training, or reinforcement learning for frontier or open-source models
• AI/ML research experience demonstrated through publications, open-source contributions, or other meaningful research impact
• Time spent at a fast-growing startup or on a high-ownership engineering team

About the company

Perplexity Computer is one of the defining products of the new era of agentic AI. Millions of people use Perplexity to transform knowledge into action.