Member of Technical Staff (Applied AI Engineer, Agent Capabilities)
Perplexity21 hours ago
Base Salary
$220k - $405k/yr
Responsibilities
- Evaluate frontier models against real user tasks and turn promising capabilities into production agent systems.
- Improve agent planning, tool use, context management, error recovery, and long-running task execution.
- Build scalable capabilities including skills, plugins, artifact generation, auto-research, and multi-agent collaboration.
- Own agent behavior end-to-end across user-facing products, interfaces, backend services, evaluations, launches, monitoring, and iteration.
- Define offline and online evaluations for task completion, correctness, safety, latency, cost, and user satisfaction.
- Build permissions, safeguards, tracing, replay, monitoring, and other infrastructure for secure and reliable agent systems.
- Collaborate with product management, data science, and research to identify opportunities and productize emerging model behaviors.
- Set technical direction on ambiguous problems and contribute through design reviews, mentorship, and technical leadership.
Requirements
- 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 and experience with AI/ML products, backend services, or distributed systems at scale.
- Experience owning the AI product lifecycle, including data analysis, rigorous evaluation, production monitoring, and iterative improvement.
- Practical experience with areas such as agent harnesses, tool use, context engineering, model evaluation, browser automation, or long-running task execution.
- Ability to translate ambiguous user needs into applied AI or ML problems and ship durable solutions with measurable user impact.
- Genuine interest in frontier AI capabilities, agent systems, and rapidly evaluating and productizing new model behaviors.
- Experience with LLM context or harness engineering, subagents, coding assistants, autonomous task execution, agent safeguards, evaluation infrastructure, or production observability is beneficial.
- Familiarity with current model families, and experience with mid-training, post-training, reinforcement learning, or AI/ML research, are nice to have.
- Startup experience or experience on a high-ownership engineering team is nice to have.
Benefits
- The role emphasizes high ownership, technical craftsmanship, entrepreneurship, scholarship, and close collaboration with talented peers.
Tech Stack
Categories
About Perplexity
Perplexity builds an AI-powered answer engine for web and mobile and an enterprise product, Perplexity Computer, for AI-driven workflows across tools and apps. The company monetizes through individual subscriptions (Perplexity Pro) and enterprise plans. Founded in 2022 and headquartered in San Francisco, it operates as a privately held company.